Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsBlogSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 51892
    Prev
    Next
    INDEX
    Explanations

    elements related to cuisine and culinary experiences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    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
     ModelExpression
    -0.66
    complexContent
    -0.58
    addPreferredGap
    -0.52
     cil
    -0.52
    exitRule
    -0.51
    RectangleBorder
    -0.51
     Италијани
    -0.51
     OPTION
    -0.49
    ſammen
    -0.48
     impro
    -0.48
    POSITIVE LOGITS
    :✨
    0.41
     viață
    0.40
    getJSONArray
    0.37
     auténtica
    0.36
    glMatrixMode
    0.36
     morado
    0.35
     cherchés
    0.34
    期刊论文
    0.34
     kaynağından
    0.34
     voors
    0.34
    Activations Density 0.049%

    No Known Activations