youtube
Learn how per-layer embeddings, or PLE, work in Gemma 4 E2B and E4B, Google's open source language model. Google DeepMind’s Maarten Grootendorst breaks down how PLE gives each token a layer-specific embedding for more diverse representation, boosting model performance without increasing the parameters used during computation.
Subscribe to Google for Developers →
Products Mentioned: Gemma 4
Speaker: Maarten Grootendorst
|
2026/09/25
youtube
