© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-3-4B-IT
    3. 9-GEMMASCOPE-2-RES-16K
    4. 302
    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_9_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
    তে
    1.23
    leş
    1.17
     unha
    1.08
    ваме
    1.06
    ために
    1.04
    콩
    1.02
     propriété
    1.00
    что
    1.00
     laag
    1.00
    IFORNIA
    0.99
    POSITIVE LOGITS
    ک
    1.25
     बैठकर
    1.21
     alertness
    1.20
    RR
    1.20
     awhile
    1.18
    湎
    1.15
    पटॉप
    1.10
     splitpos
    1.09
    骈
    1.07
     bored
    1.06
    Activations Density 3.439%

    No Known Activations