Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 22-GEMMASCOPE-TRANSCODER-16K
    4. 14486
    Prev
    Next
    INDEX
    Explanations

    mentions of the name "David" followed by another word

    oai_token-act-pair · gemini-2.0-flash

    David

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
     internasional
    -0.40
     raggiung
    -0.39
    方
    -0.39
     offent
    -0.38
    2
    -0.38
     fundido
    -0.37
     lumea
    -0.37
     perang
    -0.37
    řízen
    -0.37
     that
    -0.36
    POSITIVE LOGITS
     للمعارف
    1.02
    IndentedString
    0.97
     متعلقه
    0.92
    Autoritní
    0.92
    SharedCtor
    0.91
     Roskov
    0.90
    extAlignment
    0.89
     iNdEx
    0.89
    rungsseite
    0.88
    RTEE
    0.86
    Activations Density 0.315%

    No Known Activations