© 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. 104904
    Prev
    Next
    INDEX
    Explanations

    questions and phrases related to challenges or obstacles

    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
     and
    -0.40
    ,
    -0.35
     finally
    -0.29
     bolt
    -0.29
    moz
    -0.28
    .
    -0.28
     board
    -0.27
     character
    -0.27
     silver
    -0.27
     draft
    -0.27
    POSITIVE LOGITS
     ब्रेकडाउन
    0.78
     Chwiliwch
    0.75
    ConstraintMaker
    0.75
    rungsseite
    0.73
    majánló
    0.72
     パンチラ
    0.72
    Jeografia
    0.72
    <unused43>
    0.71
     Dieſe
    0.71
    <pad>
    0.71
    Activations Density 0.079%

    No Known Activations