© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 115280
    Prev
    Next
    INDEX
    Explanations

    function definitions and their closing brackets

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

    print, def, demo

    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
    Not in Any Lists

    No Comments

    Negative Logits
    Datuak
    -0.81
     kasarigan
    -0.79
     utafitiHapana
    -0.70
    ftagPool
    -0.65
    참고
    -0.65
    fillType
    -0.65
    
    -0.64
     يتيمه
    -0.63
    帖最后由
    -0.63
     للاسماء
    -0.62
    POSITIVE LOGITS
    Preço
    0.36
     Biôgrafia
    0.32
     anbef
    0.30
    Discard
    0.29
     déchir
    0.28
     procedimiento
    0.27
     vicenda
    0.27
    ์ตูน
    0.27
     almend
    0.27
     témoignage
    0.26
    Activations Density 0.006%

    No Known Activations