© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 10678
    Prev
    Next
    INDEX
    Explanations

    keywords and phrases related to thread management and task execution in programming

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

    Waiting, sleeping, or asynchronous tasks

    np_acts-logits-general · gemini-2.0-flash

    waiting, sleeping, and delaying

    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-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91
    Prompts (Dashboard)
    24,576 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
     ModelExpression
    -0.68
    TagMode
    -0.52
    Tembelea
    -0.46
    didSet
    -0.45
    EndInit
    -0.44
    MLLoader
    -0.43
     NSCoder
    -0.43
    存于互联网档案馆
    -0.39
     myſelf
    -0.39
    htbp
    -0.38
    POSITIVE LOGITS
     WebDriverWait
    0.53
    warten
    0.48
    attendre
    0.47
     menunggu
    0.47
    ruptedException
    0.46
    WaitGroup
    0.46
    jsonwebtoken
    0.46
    endmodule
    0.45
    AndWait
    0.45
     démocratique
    0.45
    Activations Density 0.288%

    No Known Activations