OBJECTIVE To test associations and interactions between racial identification, neighborhood risk, and low birth weight disparities between infants born to African-American and white adolescent mothers. METHODS Retrospective cross-sectional study. Birth cases were geocoded and linked to census tract information from the 2010 US Census and the 2007-2011 American Community Survey. A "neighborhood risk" index was created using principal component analysis, and mothers were grouped into 3 neighborhood risk levels (low, medium, high). Multilevel models with cross-level interactions were used to identify variation in racial differences in low birth weight outcomes across neighborhood risk levels when controlling for maternal demographic characteristics and pregnancy behaviors (smoking, prenatal care use). METHODS North Carolina, United States. METHODS Singleton infants (n = 7923 cases) born to non-Hispanic African American and white adolescent mothers from the North Carolina State Center of Health Statistics for 2011. METHODS Low birth weight. RESULTS African American mothers were significantly more likely to have infants of low birth weight than white mothers in this sample (odds ratio = 1.89; 95% confidence interval, 1.53-2.34). Mothers that resided in areas of high neighborhood risk were significantly more likely to have infants of low birth weight than mothers residing in areas of low neighborhood risk (odds ratio = 1.55; 95% confidence interval, 1.25-1.93). Even when controlling for confounding factors, racial disparities in low birth weight odds did not significantly vary according to neighborhood risk level. CONCLUSIONS Racial disparities can remain in low birth weight odds among infants born to adolescent mothers when controlling for maternal characteristics, pregnancy behaviors, and neighborhood risk.