© 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. 19-GEMMASCOPE-TRANSCODER-16K
    7. 7712
    Prev
    Next
    INDEX
    Explanations

    This neuron seems to be matching two unrelated topics: The first trigger is around a description of periscopes, specifically when they are being retracted, and the second trigger is around walking the dogs

    oai_token-act-pair · gemini-2.0-flash

    Retraction and storage

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_19/width_16k/average_l0_12
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.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
    ValueStyle
    -0.81
     snippetHide
    -0.73
    tagHelper
    -0.69
     '{@
    -0.69
    DoubleQuotes
    -0.66
    AnchorStyles
    -0.66
     ExecuteAsync
    -0.66
     PhpStorm
    -0.64
    SOUNDBITE
    -0.63
    athyroid
    -0.62
    POSITIVE LOGITS
    收回
    0.64
     retra
    0.63
     storage
    0.63
     retracted
    0.63
     Storage
    0.58
    收
    0.58
    เก็บ
    0.58
    principalColumn
    0.57
    Storage
    0.57
     retract
    0.57
    Activations Density 1.240%

    No Known Activations