© 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. 20-GEMMASCOPE-RES-131K
    11. 56031
    Prev
    Next
    INDEX
    Explanations

    technical terms related to system timing and clock management in programming

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

    timekeeping functions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    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
    AdapterView
    -0.38
     Scha
    -0.37
    charpe
    -0.35
     BAC
    -0.35
     assembled
    -0.33
     partners
    -0.33
     ش
    -0.33
    👖
    -0.32
    KeySpec
    -0.32
     BNF
    -0.32
    POSITIVE LOGITS
    reportWebVitals
    0.65
    MemoryWarning
    0.60
     timeval
    0.58
     measurement
    0.57
    gettimeofday
    0.56
    relativeTime
    0.56
     Stopwatch
    0.54
    CloseOperation
    0.52
    Clock
    0.52
     mesurer
    0.51
    Activations Density 0.038%

    No Known Activations