Abstract Study Objectives Sleep stage scoring is performed manually by sleep experts and is prone to subjective interpretation of scoring rules with low intra- and interscorer reliability. Many automatic systems rely on few small-scale databases for developing models, and generalizability to new datasets is thus unknown. We investigated a novel deep neural network to assess the generalizability of several large-scale cohorts. Methods A deep neural network model was developed using 15,684 polysomnography studies from five different cohorts. We applied four different scenarios: (1) impact of varying timescales in the model; (2) performance of a single cohort on other cohorts of smaller, greater, or equal size relative to the performance of other cohorts on a single cohort; (3) varying the fraction of mixed-cohort training data compared with using single-origin data; and (4) comparing models trained on combinations of data from 2, 3, and 4 cohorts. Results Overall classification accuracy improved with increasing fractions of training data (0.25%: 0.782 ± 0.097, 95% CI [0.777–0.787]; 100%: 0.869 ± 0.064, 95% CI [0.864–0.872]), and with increasing number of data sources (2: 0.788 ± 0.102, 95% CI [0.787–0.790]; 3: 0.808 ± 0.092, 95% CI [0.807–0.810]; 4: 0.821 ± 0.085, 95% CI [0.819–0.823]). Different cohorts show varying levels of generalization to other cohorts. Conclusions Automatic sleep stage scoring systems based on deep learning algorithms should consider as much data as possible from as many sources available to ensure proper generalization. Public datasets for benchmarking should be made available for future research.