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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 131k
    5. 31-GEMMASCOPE-RES-131K
    6. 21440
    Prev
    Next
    INDEX
    Explanations

    various function and method signatures in programming code

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

    programming constructs like interfaces and functions

    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-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_31/width_131k/average_l0_109
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    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
    ArrowToggle
    -0.50
     OMITBAD
    -0.46
    because
    -0.42
    SqlClient
    -0.42
     gynhyrchwyd
    -0.41
     {?>
    -0.41
     Çünkü
    -0.40
    EnableWeb
    -0.40
    畢竟
    -0.39
    __(/*!
    -0.39
    POSITIVE LOGITS
     EconPapers
    0.58
    throws
    0.44
     throws
    0.43
    ğlık
    0.41
    reonine
    0.41
    Throws
    0.40
     devono
    0.40
     must
    0.39
    void
    0.39
    KommentareTeilen
    0.39
    Activations Density 0.007%

    No Known Activations