© 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. 104895
    Prev
    Next
    INDEX
    Explanations

    phrases indicating causation or explanation

    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
     мәкал
    -0.67
    GEBURTSDATUM
    -0.60
     ſche
    -0.60
     nakalista
    -0.60
     trapez
    -0.59
    mator
    -0.58
    ollectionView
    -0.57
     Arme
    -0.57
    Попис
    -0.57
    ſelves
    -0.56
    POSITIVE LOGITS
     because
    0.46
     mengingat
    0.45
     owing
    0.41
     cuarzo
    0.39
     Tatsache
    0.38
     reason
    0.38
     powodu
    0.36
     rodillas
    0.36
     disebabkan
    0.36
    是因为
    0.36
    Activations Density 0.088%

    No Known Activations