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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 6109
    Prev
    Next
    INDEX
    Explanations

    phrases related to paying attention

    oai_token-act-pair · gemini-2.0-flash

    variations of the word "attention"

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

    paying attention

    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
     mukana
    -0.44
    rippa
    -0.44
    ásban
    -0.43
    EPI
    -0.43
    eaus
    -0.43
    웃
    -0.42
    endregion
    -0.42
     CURIAM
    -0.41
    oughlin
    -0.41
    Description
    -0.41
    POSITIVE LOGITS
     atte
    0.77
     Atten
    0.75
     atten
    0.71
     att
    0.70
     attent
    0.68
     Att
    0.66
    Att
    0.66
    WithIOException
    0.64
    tention
    0.64
     المعيارى
    0.62
    Activations Density 1.144%

    No Known Activations