© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 4-GEMMASCOPE-TRANSCODER-16K
    7. 9234
    Prev
    Next
    INDEX
    Explanations

    the word "head" and related words in different contexts.

    oai_token-act-pair · gemini-2.0-flash

    Head

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
     head
    -3.13
    Head
    -2.75
     Head
    -2.72
    head
    -2.70
     heads
    -2.47
     HEAD
    -2.45
    HEAD
    -2.34
    heads
    -2.17
     Heads
    -2.06
    Heads
    -1.95
    POSITIVE LOGITS
    GraphicsUnit
    0.57
    EFIAPI
    0.56
    \}=
    0.52
     digitais
    0.51
    ccional
    0.51
    bital
    0.50
    /******/
    0.48
     урна
    0.48
    صیل
    0.48
    たぶん
    0.48
    Activations Density 2.997%

    No Known Activations