Scaling works in biology if you use latents

Scaling is a dominant paradigm in the field of artificial intelligence. Despite the advantages of scaling in computer vision and large language models, recent studies have shown that scaling models trained on genome and protein sequences plateau in performance when evaluating mutational effects in the zero-shot setting. This zero-shot setting compares the likelihood of a variant sequence and its wildtype sequence, under the assumption that likelihood is a proxy for general fitness. The likelihood is based solely on the probability that a sequence, $p(sequence)$, occurs in the distribution of the data on which the model is trained. This largely ignores the biological context of the variant, leading to poor prediction of mutational effects on phenotypes such as enzymatic catalytic activity. Here we show that simple supervised probes fitted to frozen model representations reveal scaling gains in phenotype prediction that zero-shot likelihood misses. By examining the latent space of protein and genome language models across different scales and deep mutational scanning benchmarks, we restore the gains that should be expected from scaling.