© 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. 97034
    Prev
    Next
    INDEX
    Explanations

    references to commands and configurations related to a technical system or programming context

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

    code structure indicators

    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
    InjectAttribute
    -0.83
     faſt
    -0.71
    BeginInit
    -0.67
     snippetHide
    -0.66
     myſelf
    -0.64
     ſeveral
    -0.63
    GraphicsUnit
    -0.62
     autorytatywna
    -0.62
    QMetaType
    -0.62
     Infór
    -0.60
    POSITIVE LOGITS
    _
    0.69
    ogue
    0.52
    ency
    0.50
     
    0.50
     اله
    0.49
    orial
    0.48
     Portal
    0.47
     Rog
    0.47
    ‌
    0.47
    setcounter
    0.47
    Activations Density 0.167%

    No Known Activations