© 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
    7. Residual Stream - 16k
    9. 31-GEMMASCOPE-RES-16K
    11. 3173
    Prev
    Next
    INDEX
    Explanations

    programming constructs related to button actions and user interactions in a graphical user interface

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

    user interface button and dialog component declarations in code.

    oai_token-act-pair · claude-4-5-haiku
    Triggered by @emiglarou
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_31/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
     يتيمه
    -0.47
     ModelExpression
    -0.40
    usermodel
    -0.37
    الحياه
    -0.35
    elemField
    -0.35
    Geplaatst
    -0.33
    ❞
    -0.33
    "';
    -0.29
    Vanjske
    -0.28
    posedge
    -0.28
    POSITIVE LOGITS
     cancel
    0.99
     OK
    0.91
     Cancel
    0.86
    Cancel
    0.83
     reset
    0.83
     ok
    0.83
     CANCEL
    0.81
     okay
    0.81
     quit
    0.80
     Quit
    0.79
    Activations Density 0.279%

    No Known Activations