© 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. 34245
    Prev
    Next
    INDEX
    Explanations

    issues related to programming logic and data handling conflicts

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

    some sort of uncertainty

    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
    Negative Logits
    endorong
    -0.41
    時も
    -0.33
     يلي
    -0.31
    だけでなく
    -0.30
    Referințe
    -0.30
     dubbio
    -0.29
     graças
    -0.29
    >()
    -0.29
     razie
    -0.28
    Fns
    -0.28
    POSITIVE LOGITS
     somehow
    2.80
     Somehow
    2.23
     somewhere
    2.13
     something
    2.13
    Somehow
    2.06
    something
    1.98
    somewhere
    1.86
    Something
    1.84
     Something
    1.83
     quelque
    1.79
    Activations Density 0.531%

    No Known Activations