© 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. 101128
    Prev
    Next
    INDEX
    Explanations

    function signatures or method definitions in code

    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
    parsedMessage
    -0.99
    iſchen
    -0.91
    ſſung
    -0.84
    <unused52>
    -0.84
    <unused68>
    -0.84
    <unused14>
    -0.84
    <unused79>
    -0.84
    <unused8>
    -0.84
    [@BOS@]
    -0.84
    <unused3>
    -0.84
    POSITIVE LOGITS
     reviewed
    0.30
      
    0.28
     you
    0.27
    \
    0.27
    لينكات
    0.26
     yo
    0.25
     that
    0.25
    Để
    0.25
     Ön
    0.25
    0.24
    Activations Density 0.026%
    No Known Activations