© 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. 108028
    Prev
    Next
    INDEX
    Explanations

    references to programming constructs, specifically related to actions and asynchronous operations

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

    programming constructs like action, runnable, or loops

    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
    oglobulin
    -0.49
     onCreateView
    -0.47
     naturais
    -0.47
     trabalhadores
    -0.45
    返回值
    -0.45
    rzost
    -0.44
     vocês
    -0.44
    EFIAPI
    -0.44
     refroid
    -0.44
    adillas
    -0.44
    POSITIVE LOGITS
    SharedDtor
    0.49
    parsedMessage
    0.48
    WaitGroup
    0.46
    PrintStream
    0.45
     defaultstate
    0.44
    UseVisualStyle
    0.44
    forEach
    0.43
    اریخ
    0.42
    WriteBarrier
    0.42
    ệc
    0.40
    Activations Density 0.003%

    No Known Activations