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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 22-GEMMASCOPE-2-RES-16K
    7. 607
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-pt/resid_post/layer_22_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    €¦
    0.98
    <unused2012>
    0.89
    ੍ਰ
    0.88
    <unused2023>
    0.87
    <unused1997>
    0.85
    ከር
    0.85
    <unused961>
    0.85
    <unused2071>
    0.85
    <unused1015>
    0.85
    ኾ
    0.84
    POSITIVE LOGITS
     “
    4.68
     "
    4.62
     “‘
    4.07
     „
    4.06
     «
    4.04
     "'
    3.92
     “[
    3.87
     ‘‘
    3.86
     ''
    3.81
     ‘
    3.81
    Activations Density 6.170%

    No Known Activations