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. 1111
    Prev
    Next
    INDEX
    Explanations

    mentions of formal events with known dates

    oai_token-act-pair · 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
     recently
    -0.50
     Recently
    -0.44
    lorus
    -0.44
    ียด
    -0.43
     recent
    -0.43
    amoan
    -0.41
    נת
    -0.41
    avoit
    -0.41
     recente
    -0.40
     réputation
    -0.40
    POSITIVE LOGITS
    ValueStyle
    1.16
    SourceChecksum
    0.93
    UnsafeEnabled
    0.79
     autorytatywna
    0.79
    tagHelperRunner
    0.77
    AnchorStyles
    0.74
     متعلقه
    0.73
    ::_('
    0.72
    StoryboardSegue
    0.72
     للاسماء
    0.72
    Activations Density 17.633%

    No Known Activations