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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 16k
    5. 31-GEMMASCOPE-RES-16K
    6. 15913
    Prev
    Next
    INDEX
    Explanations

    programming constructs and function definitions related to asynchronous operations

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

    Code-related terms: "return", "parser", "Scanner", etc

    np_acts-logits-general · gemini-2.0-flash

    Java method returns

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_31/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Normdatei
    -0.67
    WithIOException
    -0.59
    ValueStyle
    -0.57
     BorderSide
    -0.57
     يتيمه
    -0.54
    المناصب
    -0.53
     مشين
    -0.51
     BoxFit
    -0.50
    IntoConstraints
    -0.50
    MemoryWarning
    -0.50
    POSITIVE LOGITS
     finally
    0.44
    Finally
    0.40
    addTo
    0.38
     Finally
    0.37
     Selanjutnya
    0.36
    //}
    0.35
    copyTo
    0.35
     따라
    0.34
    setattr
    0.34
    DataTo
    0.34
    Activations Density 0.267%

    No Known Activations