© 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. 128788
    Prev
    Next
    INDEX
    Explanations

    keywords and terms associated with the GTK graphical user interface toolkit

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

    gtk_

    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
    Negative Logits
    ferous
    -0.32
     proposées
    -0.31
     cantantes
    -0.31
     sáb
    -0.31
     respaldo
    -0.30
     valsty
    -0.30
     atve
    -0.30
     products
    -0.29
     présents
    -0.29
     tuot
    -0.29
    POSITIVE LOGITS
    CloseOperation
    1.60
     gtk
    1.24
     Gtk
    1.10
    gtk
    1.07
    Blazor
    1.05
    Gtk
    0.99
     GTK
    0.95
     endblock
    0.93
    GTK
    0.81
    omock
    0.78
    Activations Density 0.008%

    No Known Activations