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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-3-4B-IT
    3. 22-GEMMASCOPE-2-RES-16K
    4. 775
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/resid_post/layer_22_width_16k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    {},
    0.77
    exists
    0.68
    otomy
    0.66
     leeway
    0.66
    issue
    0.64
    swap
    0.63
    daughter
    0.62
    二是
    0.62
    exit
    0.61
    ian
    0.61
    POSITIVE LOGITS
    </h2>
    1.49
     निम्नलिखित
    1.34
    ↵↵
    1.23
    </h3>
    1.23
     以下
    1.20
     Things
    1.18
     নিম্নলিখিত
    1.16
     følgende
    1.15
     aşağıdaki
    1.14
     다음과
    1.13
    Activations Density 3.037%

    No Known Activations