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. 6880
    Prev
    Next
    INDEX
    Explanations

    terminology related to polymers, resins, and chemical processes, especially cross-linking and curing

    oai_token-act-pair · gemini-2.0-flash

    polymers research publications

    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
    VIAF
    -0.60
     <>",
    -0.49
     GenerationType
    -0.46
    SizeF
    -0.46
    haustible
    -0.46
     احت
    -0.45
     Crowe
    -0.43
    الحياه
    -0.43
    stateProvider
    -0.43
     VIAF
    -0.43
    POSITIVE LOGITS
     CreateTagHelper
    0.64
     myſelf
    0.62
    olymers
    0.60
     purpoſe
    0.59
    WireFormatLite
    0.57
     ErrIntOverflow
    0.56
     themſelves
    0.56
     Imre
    0.55
     himſelf
    0.54
     ſeveral
    0.54
    Activations Density 1.492%

    No Known Activations