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
20-GEMMASCOPE-RES-16K
4155
Prev
Next
MODEL
20-gemmascope-res-16k
Source/SAE
INDEX
Go
Explanations
elements related to code and programming structures
oai_token-act-pair · gpt-4o-mini
Triggered by @bot
No Scores
Follows a colon and a space
np_acts-logits-general · gemini-2.0-flash
No Scores
self-referential terms
np_acts-logits-general · gemini-2.5-flash-lite
No Scores
New Auto-Interp
AutoInterp Type
claude-4-5-haiku
Generate
Top Features by Cosine Similarity
Comparing With
GEMMA-2-2B @ 20-gemmascope-res-16k
Configuration
google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
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.20.hook_resid_post
Hook Layer
20
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/20-gemmascope-res-16k/4155?embed=true&embedexplanation=true&embedplots=true&embedtest=true" title="Neuronpedia" style="height: 300px; width: 540px;"></iframe>
Link
https://www.neuronpedia.org/gemma-2-2b/20-gemmascope-res-16k/4155?embed=true&embedexplanation=true&embedplots=true&embedtest=true
Not in Any Lists
Add to List
▼
No Comments
ADD
Negative Logits
-1.03
(
-0.89
"
-0.88
,
-0.86
in
-0.84
a
-0.82
vi
-0.81
-0.79
“
-0.78
y
-0.78
POSITIVE LOGITS
Reſ
2.19
Anſ
2.17
ſelves
2.14
Efq
2.14
Houſe
2.13
ſelf
2.12
Jefus
2.10
Monfieur
2.10
itſelf
2.09
myſelf
2.07
Act
ivations
Density 1.038%
Test
Steer
Stacked
Snippet
Full
Show Raw Tokens
Show Formatted
Show Breaks
Hide Breaks
No Known Activations
