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. 20-GEMMASCOPE-TRANSCODER-16K
    4. 16141
    Prev
    Next
    INDEX
    Explanations

    words related to the mechanics and physical properties of bone and screws, especially in a research context

    oai_token-act-pair · gemini-2.0-flash

    Model

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_20/width_16k/average_l0_11
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.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
    printStackTrace
    -0.77
    onViewCreated
    -0.73
    WebMethod
    -0.70
     Wikimedijinoj
    -0.67
     MainAxisSize
    -0.65
    mazoo
    -0.63
    RegressionTest
    -0.63
     mergeFrom
    -0.60
    曖昧さ回避
    -0.60
     WaitForSeconds
    -0.59
    POSITIVE LOGITS
     model
    0.50
     models
    0.49
     endforeach
    0.47
    MessageTagHelper
    0.47
    modelle
    0.46
    model
    0.46
     fjor
    0.46
     layer
    0.44
     shel
    0.43
     Neo
    0.43
    Activations Density 4.074%

    No Known Activations