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. 19-GEMMASCOPE-TRANSCODER-16K
    4. 10102
    Prev
    Next
    INDEX
    Explanations

    The neuron finds instances of the abbreviation "al" which is often part of a last name in academic citations.

    oai_token-act-pair · gemini-2.0-flash

    Scientific papers

    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
    ancourt
    -0.45
    annia
    -0.44
    ését
    -0.41
    titious
    -0.40
     déb
    -0.40
     honn
    -0.39
     Engineer
    -0.39
    ancey
    -0.39
    isance
    -0.38
    宜
    -0.38
    POSITIVE LOGITS
     مرئيه
    0.81
    posedge
    0.74
    mybatisplus
    0.68
    ."));
    0.67
     فريبيس
    0.65
    nloa
    0.62
    ContentAsync
    0.60
    multer
    0.60
    StreetMap
    0.60
    .)}
    0.59
    Activations Density 0.059%

    No Known Activations