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. 990
    Prev
    Next
    INDEX
    Explanations

    C++ code syntax, specifically variable declarations and includes

    oai_token-act-pair · gemini-2.0-flash

    int

    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
    INTS
    -0.61
    int
    -0.54
     int
    -0.52
    INT
    -0.49
    chaf
    -0.48
     selera
    -0.48
    ints
    -0.47
     getPrice
    -0.46
    DropTable
    -0.45
    이스
    -0.45
    POSITIVE LOGITS
     CreateTagHelper
    0.74
    ModelAttribute
    0.58
    #+#
    0.57
     getItemId
    0.57
     FetchType
    0.56
    +#+#
    0.56
    tvguidetime
    0.55
    esModule
    0.55
    XmlAccessorType
    0.55
    kuuta
    0.54
    Activations Density 1.230%

    No Known Activations