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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 23-GEMMASCOPE-RES-16K
    6. 11263
    Prev
    Next
    INDEX
    Explanations

    references to outcomes of conflicts and competitions

    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
    IMPORTED
    -0.64
    HtmlAttribute
    -0.62
    ArgumentParser
    -0.62
    czaj
    -0.60
    исленность
    -0.57
     Transfermarkt
    -0.57
     تضيفلها
    -0.57
    endpush
    -0.54
    Ủ
    -0.54
    setVerticalGroup
    -0.53
    POSITIVE LOGITS
     win
    2.66
     winning
    2.51
     wins
    2.44
     victory
    2.24
    win
    2.11
     winner
    2.08
    winning
    2.04
    Winning
    2.01
     winners
    1.99
     WIN
    1.93
    Activations Density 0.347%

    No Known Activations