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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 29205
    Prev
    Next
    INDEX
    Explanations

    terms related to card games and game mechanics

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

    card games and cycles

    np_acts-logits-general · gemini-2.5-flash-lite
    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
    NewReader
    -0.48
     للاسماء
    -0.48
    omitempty
    -0.46
     PopupWindow
    -0.45
    ekwondo
    -0.45
    RenderAtEndOf
    -0.45
    ScopeManager
    -0.44
    marathon
    -0.44
    FormTagHelper
    -0.43
    DockStyle
    -0.42
    POSITIVE LOGITS
     ModelExpression
    0.40
     مرئيه
    0.39
    amélioration
    0.38
     aleación
    0.38
     مناط
    0.35
     cajones
    0.35
     recompensa
    0.34
     highest
    0.34
    صالات
    0.33
     réparation
    0.33
    Activations Density 0.011%

    No Known Activations