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. 0-GEMMASCOPE-TRANSCODER-16K
    4. 7193
    Prev
    Next
    INDEX
    Explanations

    strings of digits, especially years or measurement values, often containing the digit '6', '7', '8', or '9'

    oai_token-act-pair · gemini-2.0-flash

    8

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
    1
    -2.58
    2
    -2.56
    3
    -2.50
    4
    -2.41
    0
    -2.41
    8
    -2.38
    5
    -2.38
    9
    -2.33
    6
    -2.25
    7
    -2.20
    POSITIVE LOGITS
    ^(@)
    2.48
    BibitemShut
    2.28
     Efq
    2.22
    %\]
    2.19
    .}~\
    2.16
    )";
    
    2.16
    )");
    
    2.11
    %");
    2.09
    — 
    2.09
    "):
    
    2.09
    Activations Density 4.296%

    No Known Activations