© 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. 31-GEMMASCOPE-RES-131K
    11. 34520
    Prev
    Next
    INDEX
    Explanations

    references related to code or programming interfaces

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

    remote process designation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 31-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_31/width_131k/average_l0_109
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    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
    Not in Any Lists

    No Comments

    Negative Logits
    #+#
    -0.44
     neighbors
    -0.42
     ign
    -0.35
     getItemCount
    -0.35
    катери
    -0.34
     Quebec
    -0.34
     Québec
    -0.34
     MaterialApp
    -0.34
    harusnya
    -0.34
     RSS
    -0.33
    POSITIVE LOGITS
     autorytatywna
    0.69
    RemoteException
    0.67
     RemoteException
    0.66
    adpleegd
    0.60
    الحياه
    0.59
    RectangleBorder
    0.53
     DESCRIP
    0.51
    thums
    0.48
    Autoritní
    0.47
     getService
    0.46
    Activations Density 0.001%

    No Known Activations