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-IT
    4. Residual Stream - 16k
    5. 31-GEMMASCOPE-RES-16K
    6. 15389
    Prev
    Next
    INDEX
    Explanations

    references to fish

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

    fish or fish-related topics

    np_acts-logits-general · gemini-2.0-flash

    fish

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_31/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    setVerticalGroup
    -0.38
    üyor
    -0.38
    ViewImports
    -0.34
    AGEM
    -0.34
    UDES
    -0.34
     przód
    -0.34
    adera
    -0.33
    ată
    -0.32
    ORING
    -0.31
    نى
    -0.31
    POSITIVE LOGITS
    Fish
    0.91
     Fish
    0.87
    fish
    0.77
    FISH
    0.77
     fish
    0.77
     FISH
    0.75
    🐟
    0.75
     Fisherman
    0.71
     Fishes
    0.70
    fishes
    0.70
    Activations Density 0.036%

    No Known Activations