© 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. 9-GEMMASCOPE-RES-131K
    11. 81475
    Prev
    Next
    INDEX
    Explanations

    mentions of features or attributes in a technical context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    features and field numbers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_131k/average_l0_121
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Médaille
    -0.33
     Administración
    -0.31
     Municipalidad
    -0.31
     منز
    -0.31
     muebles
    -0.30
     size
    -0.30
     väg
    -0.30
    ウンサー
    -0.28
    vedades
    -0.28
     Sculpture
    -0.28
    POSITIVE LOGITS
    features
    2.53
    Features
    1.95
     Features
    1.79
    FEATURES
    1.79
     features
    1.72
     FEATURES
    1.65
    feature
    1.44
     feature
    1.32
     fitur
    1.26
     Feature
    1.23
    Activations Density 0.004%

    No Known Activations