© 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-2-2B
    7. Residual Stream - 65k
    9. 20-GEMMASCOPE-RES-65K
    11. 3941
    Prev
    Next
    INDEX
    Explanations

    statements related to sports player actions and their experiences on the bench

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot

    omitted or excluded

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_65k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    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
    épendance
    -0.69
    теризу
    -0.51
    ESTON
    -0.48
    demic
    -0.48
     erwor
    -0.48
    kenal
    -0.48
    ICATED
    -0.48
    dshaw
    -0.47
    gebraucht
    -0.47
    nipeg
    -0.47
    POSITIVE LOGITS
     excluded
    1.97
     omitted
    1.71
     exclusion
    1.70
    excluded
    1.63
     omission
    1.57
     exclusions
    1.54
     exclude
    1.51
    Excluded
    1.50
     Exclusion
    1.44
     excludes
    1.43
    Activations Density 0.225%

    No Known Activations