© 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. 9-GEMMASCOPE-RES-131K
    11. 77958
    Prev
    Next
    INDEX
    Explanations

    references to wide character strings and related functions in programming code

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

    char *

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_131k/average_l0_121
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ब्रेकडाउन
    -0.47
    </caption>
    -0.38
     مشين
    -0.35
    WebControls
    -0.34
    ombia
    -0.32
     recu
    -0.32
    openqa
    -0.32
     epa
    -0.32
    möbel
    -0.31
    BeginInit
    -0.31
    POSITIVE LOGITS
    char
    2.73
     char
    2.73
     Char
    2.50
    Char
    2.47
    CHAR
    2.31
     CHAR
    2.22
    chars
    1.66
     charter
    1.66
     charters
    1.63
     Charter
    1.62
    Activations Density 0.006%

    No Known Activations