© 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. 58668
    Prev
    Next
    INDEX
    Explanations

    programming-related terms, particularly those associated with callable objects

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

    callable or callee definition

    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
    -
    -0.41
    if
    -0.40
     if
    -0.39
    9
    -0.37
     
    -0.34
     most
    -0.34
     noticia
    -0.33
    8
    -0.33
    0
    -0.33
    ровки
    -0.32
    POSITIVE LOGITS
     Callable
    1.72
    Callable
    1.59
    callable
    1.34
     callable
    1.34
    Calla
    0.82
     Calla
    0.79
    Diweddarwch
    0.73
    
    0.73
    原始内容存档于
    0.68
    MigrationBuilder
    0.68
    Activations Density 0.000%

    No Known Activations