Model techniques map
Techniquesmodel architecture

specific method · filed under model architecture

Per-Layer Embeddings (PLE)

An approach that gives each decoder layer its own small embedding for every token to improve parameter efficiency.

Also called per-layer embeddings.

sources
4
model
1
lab adopt it
1
strongest
core

How sources treat it

One count per evidence span, weakest treatment to strongest.

used 1core 3

Documented in

Further reading

Picked by hand, not extracted: where to read more, not evidence for anything on this page.

Evidence

4 spans quoted from the sources, strongest treatment first.

PLE gives each decoder layer its own small embedding for every token.

coremodel architecturein Gemma 4Google DeepMind

The smaller models incorporate Per-Layer Embeddings (PLE) to maximize parameter efficiency in on-device deployments. Rather than adding more layers or parameters to the model, PLE gives each decoder layer its own small embedding for every token.

coremodel architecturein Gemma 4Google DeepMind

Rather than adding more layers or parameters to the model, PLE gives each decoder layer its own small embedding for every token.

coremodel architecturein Gemma 4Google DeepMind

E2B and E4B use per-layer embeddings as in Gemma 3n [Gemma Team, 2025b], making them 2.3B and 4.5B effective out of 5B and 8B total parameters respectively.

usedmodel architecturein Gemma 4Google DeepMind

Filed alongside

Other methods under model architecture.