Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 86561
    Prev
    Next
    INDEX
    Explanations

    programming logic related to iterations and mathematical calculations

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

    code assignment and iteration

    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
     defaultstate
    -0.75
     الحره
    -0.73
     ligiloj
    -0.65
    Jîn
    -0.65
    webElementXpaths
    -0.63
     للمعارف
    -0.62
     كومونز
    -0.59
     חיצוניים
    -0.57
    KommentareTeilen
    -0.57
    WSGI
    -0.56
    POSITIVE LOGITS
    )<<
    0.29
    ARGS
    0.28
     previous
    0.28
    Ответ
    0.28
    Angeb
    0.27
     renter
    0.27
     hack
    0.26
     afterwards
    0.26
     ro
    0.26
     mass
    0.26
    Activations Density 0.008%

    No Known Activations