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. 16-GEMMASCOPE-RES-16K
    6. 6615
    Prev
    Next
    INDEX
    Explanations

    expressions of confusion or uncertainty in communication

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

    Follows questions or uncertainty

    np_acts-logits-general · gemini-2.0-flash

    asking a question, apologizing for appearance

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    parsedMessage
    -0.73
    MigrationBuilder
    -0.68
    CodeAttribute
    -0.68
    ArgumentParser
    -0.66
    BufferException
    -0.65
    CloseOperation
    -0.63
     <>",
    -0.62
    $_['
    -0.61
    তথ্যসূত্র
    -0.60
     שוליים
    -0.59
    POSITIVE LOGITS
    ScopeManager
    0.57
    behavior
    0.53
     clearly
    0.53
    clearly
    0.51
     visibly
    0.48
     appearance
    0.47
     trông
    0.47
     attract
    0.46
     appear
    0.46
    findpost
    0.45
    Activations Density 0.277%

    No Known Activations