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. 6873
    Prev
    Next
    INDEX
    Explanations

    abbreviations of nitrogen compounds and mathematical exponents, and some seemingly arbitrary words such as the Kohn-Sham Hamiltonian, Richtweg and Ubahn.

    oai_token-act-pair · gemini-2.0-flash

    Scientific texts with the letter N

    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
     judiciaire
    -0.62
     abstrait
    -0.60
     féminine
    -0.59
     suspendu
    -0.57
     drôle
    -0.55
     avoient
    -0.55
    .*")]
    -0.54
    extAlignment
    -0.54
    förs
    -0.53
     graphique
    -0.52
    POSITIVE LOGITS
     سكانية
    0.61
    antMatchers
    0.57
    tonsoft
    0.57
    oredCriteria
    0.54
    unknownFields
    0.53
     isSet
    0.51
    cupertino
    0.51
     StatelessWidget
    0.51
    ArrowToggle
    0.50
    ESTAMP
    0.50
    Activations Density 9.960%

    No Known Activations