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-2-2B
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 15343
    Prev
    Next
    INDEX
    Explanations

    C/C++ preprocessor directives, particularly #if, #else, #endif, and #ifdef statements.

    oai_token-act-pair · claude-3-5-sonnet-20240620Triggered by @bot

    conditional compilation statements and code structures in programming.

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

    software code snippets with specific formatting and syntax.

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot

    C preprocessor directives

    np_acts-logits-general · gemini-2.0-flash

    preprocessor conditional directives

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    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
     initComponents
    -0.64
    stateProvider
    -0.59
    ExecuteReader
    -0.52
    getReference
    -0.52
    ISupport
    -0.51
    setViewportView
    -0.50
    achs
    -0.50
    tanleria
    -0.49
    FailureListener
    -0.48
    tikzpicture
    -0.48
    POSITIVE LOGITS
     оригіналу
    0.75
    endif
    0.72
     שוליים
    0.69
    ifdef
    0.67
    else
    0.65
    elif
    0.62
     nahilalakip
    0.61
    ifndef
    0.57
    bardier
    0.56
    if
    0.56
    Activations Density 0.085%

    No Known Activations