© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 5954
    Prev
    Next
    INDEX
    Explanations

    references to classic video games and their gameplay elements

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

    Follows names or game titles

    np_acts-logits-general · gemini-2.0-flash

    Mario Brothers

    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
     autorytatywna
    -0.75
     ModelExpression
    -0.65
    SequentialGroup
    -0.60
    RenderAtEndOf
    -0.59
    writeFieldEnd
    -0.57
     '\\;'
    -0.56
    XmlAccessType
    -0.56
     PagesJaunes
    -0.53
    enterOuterAlt
    -0.52
    IndentedString
    -0.50
    POSITIVE LOGITS
    icoot
    0.40
     Mario
    0.36
    Tembelea
    0.36
     createSprite
    0.35
    miyor
    0.34
     exclusion
    0.31
    Mario
    0.30
    mario
    0.30
     attravers
    0.30
    adaptiveStyles
    0.30
    Activations Density 0.127%

    No Known Activations