© 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. 49238
    Prev
    Next
    INDEX
    Explanations

    measurable quantities and their relationships in scientific studies

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

    units of time and measurement

    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
     utafitiHapana
    -0.82
    featureID
    -0.81
    IntoConstraints
    -0.79
    enterOuterAlt
    -0.79
     betweenstory
    -0.75
    expandindo
    -0.73
     snippetHide
    -0.73
     виправивши
    -0.73
    oredCriteria
    -0.72
     Normdatei
    -0.71
    POSITIVE LOGITS
     standardized
    0.40
    getSettings
    0.38
     Washington
    0.38
     Free
    0.38
    umu
    0.37
     prome
    0.37
     cours
    0.37
     Daily
    0.37
     marco
    0.37
     McDonald
    0.36
    Activations Density 0.252%

    No Known Activations