© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 6-GEMMASCOPE-TRANSCODER-16K
    7. 14955
    Prev
    Next
    INDEX
    Explanations

    This neuron seems to be reacting to mathematical and technical notation, as well as section dividers.

    oai_token-act-pair · gemini-2.0-flash

    scientific methods

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_6/width_16k/average_l0_95
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.6.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
    XmlEnum
    -0.52
    UrlResolution
    -0.46
    
    -0.44
     муніципалі
    -0.40
    营
    -0.40
    HandlerContext
    -0.39
    헌
    -0.39
    انيف
    -0.39
    zzino
    -0.39
     onOptions
    -0.39
    POSITIVE LOGITS
    protoimpl
    0.71
    IndentedString
    0.71
    sizeCache
    0.69
    ⓘ
    0.65
    adaptiveStyles
    0.65
     kasarigan
    0.63
     iNdEx
    0.60
    WriteBarrier
    0.59
    WireFormatLite
    0.58
    Adults
    0.58
    Activations Density 3.206%

    No Known Activations