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. 901
    Prev
    Next
    INDEX
    Explanations

    words related to finance and investment, more broadly, economic growth and return

    oai_token-act-pair · gemini-2.0-flash

    Business/Marketing/Economics

    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
     ComVisible
    -0.88
    AccessorTable
    -0.70
    GIVEREF
    -0.70
     ujednoznacz
    -0.68
     initComponents
    -0.67
    ProgressHUD
    -0.67
    \{\\
    -0.66
    UrlResolution
    -0.65
     defaultstate
    -0.65
    smithy
    -0.65
    POSITIVE LOGITS
    werkt
    0.44
     revisor
    0.40
     -
    0.40
     llevo
    0.38
    MD
    0.38
     mutually
    0.38
    ++]=
    0.36
     le
    0.35
    mored
    0.35
    MTA
    0.34
    Activations Density 2.754%

    No Known Activations