© 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-IT
    7. Residual Stream - 131k
    9. 20-GEMMASCOPE-RES-131K
    11. 116823
    Prev
    Next
    INDEX
    Explanations

    technical terms and references related to scientific research

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    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
    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
    RTEE
    -0.45
     E
    -0.36
     AIR
    -0.34
    Ol
    -0.34
     Ol
    -0.34
     −
    -0.33
     Soft
    -0.33
    Gamma
    -0.32
     Easy
    -0.32
    iVar
    -0.32
    POSITIVE LOGITS
    httphttps
    0.73
     autorytatywna
    0.73
    CloseOperation
    0.67
     BoxDecoration
    0.63
     descrição
    0.56
     Audiodateien
    0.56
    MessageOf
    0.56
    новништво
    0.56
    contentLoaded
    0.56
     intptr
    0.55
    Activations Density 0.062%

    No Known Activations