© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 39101
    Prev
    Next
    INDEX
    Explanations

    code structures and elements related to programming and user interface interactions

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

    Android programming constructs

    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
     فريبيس
    -0.58
    见状
    -0.48
    IndentedString
    -0.48
     vapormax
    -0.48
    ️
    -0.46
    issory
    -0.46
     PeEnEo
    -0.45
     emojis
    -0.43
     للمعارف
    -0.43
     emoji
    -0.42
    POSITIVE LOGITS
    AutoField
    0.52
     useAppContext
    0.50
    MigrationBuilder
    0.49
     iPod
    0.48
    iPod
    0.45
     Offisielt
    0.43
    Abraços
    0.43
    lusconi
    0.43
     régulière
    0.43
     aDecoder
    0.42
    Activations Density 0.017%

    No Known Activations