© 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. 105030
    Prev
    Next
    INDEX
    Explanations

    content related to general news and topics of interest

    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
     Kr
    -0.23
    Consider
    -0.23
     At
    -0.23
    RTHOOK
    -0.23
    ificantly
    -0.23
    relsen
    -0.22
    こち
    -0.21
     số
    -0.21
     Bereits
    -0.21
     Sure
    -0.21
    POSITIVE LOGITS
    AddTagHelper
    0.78
     genres
    0.73
     NSCoder
    0.68
    expandindo
    0.68
    aarrggbb
    0.67
    StructEnd
    0.66
    Personensuche
    0.66
     comedies
    0.66
    istoitu
    0.65
     houſe
    0.65
    Activations Density 0.045%

    No Known Activations