Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 4-GEMMASCOPE-TRANSCODER-16K
    4. 13685
    Prev
    Next
    INDEX
    Explanations

    text clusters around the word "solution."

    oai_token-act-pair · gemini-2.0-flash

    solution

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.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
     solution
    -2.47
     solutions
    -2.27
     Solution
    -2.23
    solution
    -2.14
    Solution
    -2.11
     Solutions
    -1.99
     SOLUTION
    -1.98
    solutions
    -1.96
    Solutions
    -1.96
     Lösung
    -1.81
    POSITIVE LOGITS
    Према
    0.69
     Orrell
    0.68
    mybatisplus
    0.63
    MockBean
    0.61
    󠁢
    0.59
     وتسجيلات
    0.58
    rungsseite
    0.58
    MessageTagHelper
    0.56
    ensement
    0.55
    MenuInflater
    0.55
    Activations Density 2.680%

    No Known Activations