© 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. 106110
    Prev
    Next
    INDEX
    Explanations

    specific types of code structures or keywords in a programming context

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

    coding keywords and function names

    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
     Dafür
    -0.32
     lihat
    -0.32
     due
    -0.32
    ář
    -0.31
     yeter
    -0.30
     refusé
    -0.30
    due
    -0.29
    ground
    -0.29
     erhöhen
    -0.29
     geçen
    -0.28
    POSITIVE LOGITS
    ########.
    0.87
     autorytatywna
    0.79
    rungsseite
    0.75
     propOrder
    0.71
     للاسماء
    0.69
     صوتيه
    0.68
     مرئيه
    0.66
     &___
    0.64
    ftagPool
    0.63
    setVerticalGroup
    0.62
    Activations Density 0.021%

    No Known Activations