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. 64618
    Prev
    Next
    INDEX
    Explanations

    elements related to time management and scheduling in programming

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

    milliseconds and microseconds

    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
     hour
    -0.77
     HOUR
    -0.73
     hourly
    -0.69
     minute
    -0.68
     Hour
    -0.67
     minutes
    -0.66
    hour
    -0.64
     hours
    -0.63
    Hour
    -0.62
     Stunde
    -0.62
    POSITIVE LOGITS
    featureID
    0.39
    ciutto
    0.38
     MILL
    0.38
    Mill
    0.37
    awaiter
    0.36
    Бележки
    0.36
     reposo
    0.36
    wantErr
    0.36
    ipient
    0.36
     Mill
    0.36
    Activations Density 0.174%

    No Known Activations