© 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. 116693
    Prev
    Next
    INDEX
    Explanations

    programming-related configuration settings and debugging options

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

    debug mode

    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
    ніципалі
    -0.71
     pinulongan
    -0.63
    
    -0.60
     nahilalakip
    -0.59
    IntoConstraints
    -0.58
     autorytatywna
    -0.57
     мәкал
    -0.56
    
    -0.56
    RegistryLite
    -0.55
    Autoritní
    -0.55
    POSITIVE LOGITS
     environment
    0.40
    devtool
    0.40
     불
    0.39
    불
    0.38
     UnityEditor
    0.37
     environ
    0.34
    environment
    0.34
    Spirit
    0.33
     Spirit
    0.33
    isDebug
    0.33
    Activations Density 0.019%

    No Known Activations