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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 21-GEMMASCOPE-TRANSCODER-16K
    4. 5746
    Prev
    Next
    INDEX
    Explanations

    terms related to brain anatomy and function, especially in memory and visual processing

    oai_token-act-pair · gemini-2.0-flash

    references to specific terms or objects in research

    np_token-act-pair-logits · gpt-4o-mini

    brain functions

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    transQ
    -0.66
     '\\;'
    -0.62
     psychos
    -0.60
    invokeLater
    -0.60
     consciousness
    -0.58
     MainAxisSize
    -0.56
    WithTag
    -0.56
    ibatis
    -0.56
    psycho
    -0.56
     subconscious
    -0.55
    POSITIVE LOGITS
     getItemId
    0.56
    الحياه
    0.56
     متعلقه
    0.54
    참고
    0.54
    //
    0.53
    ylvan
    0.51
    izer
    0.49
    Counter
    0.47
     counter
    0.45
    PropertyGroup
    0.45
    Activations Density 2.393%

    No Known Activations