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. 7-GEMMASCOPE-TRANSCODER-16K
    4. 7020
    Prev
    Next
    INDEX
    Explanations

    math and physics notation, particularly those involving subscripts, superscripts, brackets, and dollar signs as well as some references to measurement.

    oai_token-act-pair · gemini-2.0-flash

    Dollar sign

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_7/width_16k/average_l0_70
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.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
     $
    -0.73
     $\
    -0.66
    qtype
    -0.55
    SourceChecksum
    -0.53
     taşı
    -0.52
    $
    -0.52
     ($
    -0.49
    />";
    -0.47
    $\
    -0.47
     format
    -0.46
    POSITIVE LOGITS
     esternos
    0.73
    IsContent
    0.72
    LookAnd
    0.58
     typelib
    0.57
     odkazy
    0.57
    ########.
    0.56
     дописавши
    0.55
     ligiloj
    0.54
     חיצוניים
    0.54
    abstractmethod
    0.54
    Activations Density 10.394%

    No Known Activations