© 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 - 16k
    9. 9-GEMMASCOPE-RES-16K
    11. 13000
    Prev
    Next
    INDEX
    Explanations

    nouns and terms associated with health and nutrition

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

    that are often followed by a measurement

    np_acts-logits-general · gemini-2.0-flash

    related quality outcome

    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-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    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
     به‌عنوان
    -0.50
    更好地
    -0.39
     dasselbe
    -0.36
     Configuración
    -0.34
     derselbe
    -0.34
    ‌شده
    -0.33
    ówczas
    -0.33
     résumé
    -0.33
     به‌
    -0.33
    olstadt
    -0.33
    POSITIVE LOGITS
     GenerationType
    0.76
     يتيمه
    0.73
     perchè
    0.71
     ++;
    0.67
    ValueStyle
    0.65
     didalam
    0.64
    weightedMode
    0.64
     poichè
    0.64
     autorytatywna
    0.62
     loosing
    0.62
    Activations Density 0.583%

    No Known Activations