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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    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. 1930
    Prev
    Next
    INDEX
    Explanations

    phrases indicating sources and origins of biological or environmental factors

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

    origin and provenance

    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
    RenderAtEndOf
    -0.36
    Rhestr
    -0.35
     sque
    -0.30
     auster
    -0.30
    screen
    -0.30
    horizontalLayout
    -0.29
     مدر
    -0.29
     holy
    -0.29
     شی
    -0.28
    Filmographie
    -0.28
    POSITIVE LOGITS
     provenientes
    0.52
     miniaturka
    0.52
     voeding
    0.52
     bezoekers
    0.51
     Contributors
    0.51
    igslist
    0.50
     procedentes
    0.50
     bezoek
    0.49
     ब्रेकडाउन
    0.48
     provenant
    0.48
    Activations Density 0.082%

    No Known Activations