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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 131k
    5. 32-GEMMASCOPE-RES-131K
    6. 130039
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "out"

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

    out and movement

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-9b-pt-res/layer_32/width_131k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.32.hook_resid_post
    Hook Layer
    32
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     <>",
    -0.52
    nloa
    -0.43
     Roskov
    -0.41
     <<<<<<<<<<<<<<
    -0.40
    EndContext
    -0.40
    seamnă
    -0.40
     ویکی‌پدیای
    -0.39
    interopRequire
    -0.38
    AndEndTag
    -0.38
    RenderAtEndOf
    -0.38
    POSITIVE LOGITS
     onto
    0.50
     туда
    0.48
    country
    0.46
     into
    0.45
     aggressively
    0.45
    AfterViewInit
    0.45
    doGet
    0.43
    ounty
    0.43
     Bisnis
    0.42
    sell
    0.42
    Activations Density 0.014%

    No Known Activations