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. 6920
    Prev
    Next
    INDEX
    Explanations

    a mix of domain-specific terms across varying topics, including genetics, coding, and chemistry

    oai_token-act-pair · gemini-2.0-flash

    biological research

    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
    Fordítás
    -0.66
     ſtand
    -0.63
     ſever
    -0.63
     preſent
    -0.63
     fhort
    -0.62
     fubject
    -0.61
     fhew
    -0.60
     Shakspeare
    -0.60
    addCriterion
    -0.59
     ſte
    -0.59
    POSITIVE LOGITS
    HostException
    0.61
     <>",
    0.60
    (!__
    0.53
    !*\
    0.51
     mouseY
    0.50
    ГЛА
    0.50
    gatsby
    0.49
    SqlClient
    0.48
    CELLANEOUS
    0.47
    <eos>
    0.47
    Activations Density 1.976%

    No Known Activations