© 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. 105529
    Prev
    Next
    INDEX
    Explanations

    references to specific individuals and their characteristics or 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
    setVerticalGroup
    -0.41
     ligiloj
    -0.40
    何况
    -0.39
     deem
    -0.37
     تكبرها
    -0.37
    RTHOOK
    -0.36
    arache
    -0.35
    Hapana
    -0.35
     guessing
    -0.34
    AsUp
    -0.34
    POSITIVE LOGITS
     fumo
    0.46
     fumée
    0.45
    occupe
    0.45
    scriptId
    0.44
     cæ
    0.43
     eſſ
    0.43
     Faites
    0.42
     Perſ
    0.42
     fusca
    0.42
     Eſ
    0.42
    Activations Density 0.036%

    No Known Activations