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. 20-GEMMASCOPE-TRANSCODER-16K
    4. 16205
    Prev
    Next
    INDEX
    Explanations

    strings consisting of periods, numbers, and forward slashes, likely identifying DOI links and file locations

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_20/width_16k/average_l0_11
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.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
    IsContent
    -0.84
     betweenstory
    -0.81
    fjspx
    -0.77
    ⓧ
    -0.71
     Audiodateien
    -0.71
     ddelweddau
    -0.66
    windowFixed
    -0.64
    ThroughAttribute
    -0.63
     propOrder
    -0.62
    posedge
    -0.59
    POSITIVE LOGITS
    zuführen
    0.56
     COA
    0.49
    riwal
    0.48
     Materiales
    0.46
     Houſe
    0.46
    aragua
    0.45
     XNUMX
    0.45
     ſeveral
    0.45
    bitkan
    0.44
     čierna
    0.44
    Activations Density 0.331%

    No Known Activations