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-2-9B-IT
Residual Stream - 131k
20-GEMMASCOPE-RES-131K
75442
Prev
Next
MODEL
20-gemmascope-res-131k
Source/SAE
INDEX
Go
Explanations
percentage-related or numerical data in the text
oai_token-act-pair · gpt-4o-mini
Triggered by @bot
No Scores
percentages and degrees
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-2-9B-IT @ 20-gemmascope-res-131k
Configuration
google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
How To Load
Prompts (Dashboard)
24,576 prompts, 128 tokens each
Dataset (Dashboard)
monology/pile-uncopyrighted
Features
131,072
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
Show Plots
Show Explanation
Show Activations
Show Test Field
Show Steer
Show Link
IFrame
<iframe src="https://www.neuronpedia.org/gemma-2-9b-it/20-gemmascope-res-131k/75442?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-2-9b-it/20-gemmascope-res-131k/75442?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
出版年
-0.60
']
-0.60
'>
-0.56
]
-0.55
']
-0.55
]
-0.55
"])
-0.54
}}$
-0.54
"]
-0.53
"]
-0.53
POSITIVE LOGITS
€,
0.62
:).
0.60
%,
0.60
…,
0.59
?,
0.57
%,
0.56
BibitemShut
0.56
(?,
0.55
...,
0.55
":"",
0.55
Act
ivations
Density 0.169%
Test
Steer
Stacked
Snippet
Full
Show Raw Tokens
Show Formatted
Show Breaks
Hide Breaks
No Known Activations
