© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 131k
    9. 20-GEMMASCOPE-RES-131K
    11. 105544
    Prev
    Next
    INDEX
    Explanations

    references to shooting and gun-related actions

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_131k/average_l0_114
    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
    Embeds
    IFrame
    Link
    Negative Logits
    AddTagHelper
    -0.65
     يتيمه
    -0.63
    ſammen
    -0.56
    onViewCreated
    -0.54
    ')[
    -0.54
    ſelben
    -0.53
     StatelessWidget
    -0.52
    SourceChecksum
    -0.52
     TestBed
    -0.52
    ')),
    -0.52
    POSITIVE LOGITS
    PerformLayout
    0.41
    heard
    0.34
    олові
    0.32
     Tiếng
    0.31
    inside
    0.31
    protective
    0.31
    cutting
    0.30
     inside
    0.29
     transcrip
    0.29
     against
    0.29
    Activations Density 0.010%

    No Known Activations