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. 4-GEMMASCOPE-TRANSCODER-16K
    4. 7789
    Prev
    Next
    INDEX
    Explanations

    mentions of time using words like 'moment', 'second', 'time', and 'once'

    oai_token-act-pair · gemini-2.0-flash

    time/counting

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.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
     itſelf
    -0.95
     myſelf
    -0.78
    RectangleBorder
    -0.78
     pleaſure
    -0.74
     himſelf
    -0.71
     themſelves
    -0.71
     gynhyrchwyd
    -0.68
    styleType
    -0.68
    Rhestr
    -0.67
     noDo
    -0.66
    POSITIVE LOGITS
    ANSAS
    0.47
    izadores
    0.45
    nargs
    0.45
    ⓧ
    0.44
     Baran
    0.44
    出版年
    0.44
    ouches
    0.43
    motic
    0.43
    ioare
    0.43
    ीक
    0.43
    Activations Density 1.341%

    No Known Activations