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. 14513
    Prev
    Next
    INDEX
    Explanations

    detailed descriptions of sports achievements

    oai_token-act-pair · 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
     ExecuteAsync
    -0.74
     NSCoder
    -0.47
    userManager
    -0.47
     DbContext
    -0.46
    PostBack
    -0.46
    ((&
    -0.46
     SqlConnection
    -0.46
     uParam
    -0.45
     EconPapers
    -0.45
    vedo
    -0.44
    POSITIVE LOGITS
    clable
    0.57
     Ente
    0.56
     fillers
    0.54
     Invitation
    0.53
    ثيق
    0.53
    IENTE
    0.52
    AndEndTag
    0.52
     initComponents
    0.52
    ARAN
    0.52
     sofia
    0.52
    Activations Density 3.105%

    No Known Activations