© 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
    3. Gemma-3-4B-IT
    5. 9-GEMMASCOPE-2-RES-16K
    7. 193
    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
    ]
    0.52
     સુધી
    0.50
    した
    0.49
    ig
    0.48
    }
    0.48
    我们
    0.44
     We
    0.44
     eventuali
    0.44
    о
    0.43
    )
    0.43
    POSITIVE LOGITS
     headquartered
    0.60
     reimag
    0.58
     notoriously
    0.58
     unveils
    0.58
     famously
    0.58
     encompasses
    0.51
    formerly
    0.50
    ்சைடு
    0.48
     മാത്രമല്ല
    0.48
     berbasis
    0.48
    Activations Density 8.874%

    No Known Activations