© 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 - 131k
    9. 20-GEMMASCOPE-RES-131K
    11. 55413
    Prev
    Next
    INDEX
    Explanations

    programming identifiers and function-related syntax in code snippets

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

    return arguments; }

    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
    rungsseite
    -0.61
     nonUne
    -0.57
     contextLoads
    -0.55
    })->
    -0.53
    MigrationBuilder
    -0.53
    ValueStyle
    -0.52
    */),
    -0.51
     تضيفلها
    -0.50
     oprot
    -0.49
    webElementXpaths
    -0.49
    POSITIVE LOGITS
    oredCriteria
    0.47
    tagext
    0.43
    wnia
    0.38
    HomeAsUpEnabled
    0.35
    Cyfarwyddwr
    0.33
    DMETHOD
    0.33
    CheckBreak
    0.31
     Absatz
    0.31
     <>",
    0.30
    Palindrome
    0.30
    Activations Density 0.046%

    No Known Activations