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. 6805
    Prev
    Next
    INDEX
    Explanations

    words related to literature, especially those used in reviews and summaries, and words indicating power, ability, or opportunity.

    oai_token-act-pair · gemini-2.0-flash

    of

    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
    endpush
    -0.56
    AddTagHelper
    -0.49
    Còn
    -0.49
     endwhile
    -0.48
    OGND
    -0.48
    WithIOException
    -0.46
     Wachs
    -0.46
    
    -0.45
    anthin
    -0.45
    viato
    -0.45
    POSITIVE LOGITS
    modelBuilder
    0.86
    contentLoaded
    0.62
     configureStore
    0.62
    ResumeLayout
    0.59
     насељу
    0.59
    MergeFrom
    0.56
     reklama
    0.55
    Personendaten
    0.54
    KURZBESCHREIBUNG
    0.54
    FieldBuilder
    0.54
    Activations Density 21.690%

    No Known Activations