© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 23-GEMMASCOPE-RES-16K
    11. 11736
    Prev
    Next
    INDEX
    Explanations

    references to the word "bear" in various contexts, including its use as a verb and within nouns

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 23-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_23/width_16k/average_l0_75
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.hook_resid_post
    Hook Layer
    23
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     متعلقه
    -0.64
     للاسماء
    -0.62
     pinulongan
    -0.62
     disambiguazione
    -0.60
     Lesley
    -0.57
     Dede
    -0.55
    ುವ
    -0.53
    ifolium
    -0.53
    ouple
    -0.52
    vinte
    -0.52
    POSITIVE LOGITS
     bear
    2.03
     bears
    1.87
     Bear
    1.82
    Bear
    1.77
     BEAR
    1.72
    bear
    1.72
     Bears
    1.69
    Bears
    1.60
    BEAR
    1.58
    bears
    1.54
    Activations Density 0.120%

    No Known Activations