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. 22-GEMMASCOPE-RES-16K
    6. 8082
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "bear" and its variations, indicating reference to the animal in various contexts

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

    "bear"

    np_acts-logits-general · gemini-2.0-flash

    bear

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     للاسماء
    -0.60
    vinte
    -0.59
     Dede
    -0.59
    iettivo
    -0.57
    entary
    -0.57
    thmus
    -0.56
    Tikang
    -0.55
    postdata
    -0.55
     Lesley
    -0.54
     متعلقه
    -0.53
    POSITIVE LOGITS
     bear
    1.93
     bears
    1.82
     Bear
    1.77
    Bear
    1.74
     BEAR
    1.69
     Bears
    1.68
    bear
    1.67
    BEAR
    1.55
    Bears
    1.53
    bears
    1.50
    Activations Density 0.090%

    No Known Activations