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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 25-GEMMASCOPE-RES-16K
    6. 3786
    Prev
    Next
    INDEX
    Explanations

    scientific terms and expressions related to poultry nutrition and health

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.hook_resid_post
    Hook Layer
    25
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     saites
    -0.60
    JSONException
    -0.58
    astify
    -0.58
    TagMode
    -0.56
    "?>
    -0.55
    BorderFactory
    -0.55
     OSError
    -0.54
    rrggbb
    -0.54
    NamedQueries
    -0.52
    AccessorTable
    -0.51
    POSITIVE LOGITS
     diets
    0.79
     feeds
    0.76
     feed
    0.75
     diet
    0.70
     ration
    0.70
     rum
    0.69
     rumen
    0.68
     Feeds
    0.67
     rou
    0.66
     rations
    0.65
    Activations Density 0.592%

    No Known Activations