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 - 65k
16-GEMMASCOPE-RES-65K
52944
Prev
Next
MODEL
16-gemmascope-res-65k
Source/SAE
INDEX
Go
Explanations
expressions of urgent emotional distress related to writing
oai_token-act-pair · gpt-4o-mini
Triggered by @bot
No Scores
personal pronouns and speech
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 @ 16-gemmascope-res-65k
Configuration
google/gemma-scope-2b-pt-res/layer_16/width_65k/average_l0_128
How To Load
Prompts (Dashboard)
24,576 prompts, 128 tokens each
Dataset (Dashboard)
monology/pile-uncopyrighted
Features
65,536
Data Type
float32
Hook Name
blocks.16.hook_resid_post
Hook Layer
16
Architecture
jumprelu
Context Size
1,024
Dataset
monology/pile-uncopyrighted
Activation Function
relu
Show All
Embeds
Show Plots
Show Explanation
Show Activations
Show Test Field
Show Steer
Show Link
IFrame
<iframe src="https://www.neuronpedia.org/gemma-2-2b/16-gemmascope-res-65k/52944?embed=true&embedexplanation=true&embedplots=true&embedsteer=true&embedactivations=true&embedlink=true&embedtest=true" title="Neuronpedia" style="height: 300px; width: 540px;"></iframe>
Link
https://www.neuronpedia.org/gemma-2-2b/16-gemmascope-res-65k/52944?embed=true&embedexplanation=true&embedplots=true&embedsteer=true&embedactivations=true&embedlink=true&embedtest=true
Not in Any Lists
Add to List
▼
No Comments
ADD
Negative Logits
.
-0.77
.")
-0.60
.”)
-0.58
.')
-0.52
.)
-0.52
_.
-0.50
arvio
-0.47
）
-0.46
.$
-0.46
.”
-0.44
POSITIVE LOGITS
,
1.05
²,
0.98
³,
0.94
++,
0.90
tagHelperRunner
0.89
€,
0.89
₂,
0.88
!,
0.88
'',
0.88
?,
0.84
Act
ivations
Density 0.058%
Stacked
Snippet
Full
Show Raw Tokens
Show Formatted
Show Breaks
Hide Breaks
No Known Activations
