© 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. 8521
    Prev
    Next
    INDEX
    Explanations

    parentheses and their variations

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

    start of turn

    np_acts-logits-general · gemini-2.5-flash-lite
    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
     betweenstory
    -1.01
     незавершена
    -0.93
     Италијани
    -0.82
     Administrativna
    -0.80
     linkovi
    -0.73
    fromnode
    -0.71
    OGND
    -0.71
     nahilalakip
    -0.70
    featureID
    -0.69
    writeFieldEnd
    -0.68
    POSITIVE LOGITS
    ########.
    0.28
    TabStop
    0.28
     Paul
    0.28
    Paul
    0.27
    :+:
    0.26
     quoi
    0.24
    venidos
    0.24
     ruinas
    0.23
    AnimationFrame
    0.23
     Polri
    0.22
    Activations Density 0.000%

    No Known Activations