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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 29502
    Prev
    Next
    INDEX
    Explanations

    syntactic structures related to method calls and task execution in code

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

    method calls or property access

    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
    SequentialGroup
    -0.69
    awtextra
    -0.56
    ########.
    -0.55
    帖最后由
    -0.54
    transQ
    -0.53
    enterOuterAlt
    -0.53
    AndEndTag
    -0.50
    UrlResolution
    -0.50
    setVerticalGroup
    -0.49
    BagLayout
    -0.49
    POSITIVE LOGITS
     Poss
    0.50
    naeus
    0.50
     Lebens
    0.49
     auth
    0.43
    caped
    0.42
     possessed
    0.42
     possess
    0.42
     posses
    0.42
    blica
    0.42
     represented
    0.41
    Activations Density 0.023%

    No Known Activations