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. 7-GEMMASCOPE-TRANSCODER-16K
    4. 6845
    Prev
    Next
    INDEX
    Explanations

    clauses of the form "that is why" or "that's why."

    oai_token-act-pair · gemini-2.0-flash

    why

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_7/width_16k/average_l0_70
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.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
    лизм
    -0.49
    AsUp
    -0.46
    taal
    -0.46
     spécial
    -0.45
    jeros
    -0.44
    zake
    -0.44
     TAMBIÉN
    -0.44
     bâton
    -0.44
    jero
    -0.44
     internetowa
    -0.44
    POSITIVE LOGITS
    ConstraintMaker
    0.90
    GOTREF
    0.66
    waitKey
    0.63
    createStatement
    0.62
     mapStateToProps
    0.59
    PreExecute
    0.59
     ComVisible
    0.58
    شهاد
    0.57
    msgTypes
    0.56
     Taktlose
    0.56
    Activations Density 4.596%

    No Known Activations