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. 8-GEMMASCOPE-TRANSCODER-16K
    4. 865
    Prev
    Next
    INDEX
    Explanations

    the presence of numbers and references to quantity, particularly in a scientific or medical context

    oai_token-act-pair · gemini-2.0-flash

    of

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_8/width_16k/average_l0_52
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.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
    Du
    -0.35
     igaz
    -0.35
     it
    -0.34
     then
    -0.33
    ↵↵
    -0.33
     Dup
    -0.33
    jspx
    -0.31
    Then
    -0.30
     sh
    -0.29
    du
    -0.29
    POSITIVE LOGITS
     виправивши
    1.08
    tagHelperRunner
    1.04
     للاسماء
    0.89
     AssemblyCulture
    0.88
     برانيه
    0.85
    yntaxException
    0.85
     initComponents
    0.84
    تقاوى
    0.83
    DockStyle
    0.83
    AndEndTag
    0.82
    Activations Density 0.322%

    No Known Activations