© 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. 9-GEMMASCOPE-RES-131K
    11. 60980
    Prev
    Next
    INDEX
    Explanations

    quantifiable metrics and statistical references related to counts or proportions

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

    only number followed by noun

    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
    Not in Any Lists

    No Comments

    Negative Logits
     multiple
    -0.38
    mbggenerated
    -0.33
    migrationBuilder
    -0.33
    хьтан
    -0.32
     fark
    -0.31
    ンス
    -0.30
     bill
    -0.30
     stream
    -0.30
     Diam
    -0.29
     multilateral
    -0.29
    POSITIVE LOGITS
    Only
    0.79
    only
    0.75
     Only
    0.70
    ONLY
    0.69
     only
    0.66
     onely
    0.66
     slechts
    0.66
     лишь
    0.62
    satunya
    0.62
     seules
    0.60
    Activations Density 0.026%

    No Known Activations