© 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
    7. Residual Stream - 16k
    9. 11-GEMMASCOPE-RES-16K
    11. 6652
    Prev
    Next
    INDEX
    Explanations

    reported speech or quotations in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 11-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_11/width_16k/average_l0_118
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Hook Layer
    11
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     للاسماء
    -0.85
    migrationBuilder
    -0.62
    SBATCH
    -0.61
     zuſammen
    -0.60
     パンチラ
    -0.60
     getCode
    -0.59
    ſchaft
    -0.59
    schrift
    -0.59
    <unused23>
    -0.58
    <unused43>
    -0.58
    POSITIVE LOGITS
     the
    0.62
     a
    0.58
     by
    0.54
     my
    0.50
     our
    0.44
     an
    0.41
     Haupt
    0.39
     said
    0.38
     Der
    0.37
     oleh
    0.36
    Activations Density 0.086%

    No Known Activations