Neuronpedia
Get Started
API
Releases
Jump To
Search
Models
Circuit Tracer
NEW
Steer
SAE Evals
Exports
Slack
Blog
Privacy & Terms
Contact
Sign In
© Neuronpedia 2025
Privacy & Terms
Blog
GitHub
Slack
Twitter
Contact
Home
Google DeepMind · Exploring Gemma 2 with Gemma Scope
Gemma-2-2B
Residual Stream - 16k
12-GEMMASCOPE-RES-16K
1418
Prev
Next
MODEL
12-gemmascope-res-16k
Source/SAE
INDEX
Go
Explanations
specific identifiers and codes related to biological and medical terminology
oai_token-act-pair · gpt-4o-mini
Triggered by @bot
No Scores
New Auto-Interp
AutoInterp Type
claude-4-5-haiku
Generate
Top Features by Cosine Similarity
Comparing With
GEMMA-2-2B @ 12-gemmascope-res-16k
Configuration
google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82
How To Load
Prompts (Dashboard)
36,864 prompts, 128 tokens each
Dataset (Dashboard)
monology/pile-uncopyrighted
Features
16,384
Data Type
float32
Hook Name
blocks.12.hook_resid_post
Hook Layer
12
Architecture
jumprelu
Context Size
1,024
Dataset
monology/pile-uncopyrighted
Activation Function
relu
Show All
Embeds
Plots
Explanation
Show Test Field
Default Test Text
IFrame
<iframe src=https://www.neuronpedia.org/gemma-2-2b/12-gemmascope-res-16k/1418?embed=true&embedexplanation=true&embedplots=true&embedtest=true" title="Neuronpedia" style="height: 300px; width: 540px;"></iframe>
Link
https://www.neuronpedia.org/gemma-2-2b/12-gemmascope-res-16k/1418?embed=true&embedexplanation=true&embedplots=true&embedtest=true
Not in Any Lists
Add to List
▼
No Comments
ADD
Negative Logits
a
-0.74
i
-0.74
o
-0.71
Ito
-0.71
ais
-0.70
drap
-0.68
ever
-0.66
Appleton
-0.64
eto
-0.64
andReturn
-0.63
POSITIVE LOGITS
hhh
1.23
hh
1.19
hhhh
1.14
Cah
1.12
rh
1.09
Rh
1.05
h
1.04
rh
1.03
Doh
1.03
TAH
1.02
Act
ivations
Density 0.494%
Test
Steer
Stacked
Snippet
Full
Show Raw Tokens
Show Formatted
Show Breaks
Hide Breaks
No Known Activations
