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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B-IT
    7. Residual Stream - 131k
    9. 20-GEMMASCOPE-RES-131K
    11. 66641
    Prev
    Next
    INDEX
    Explanations

    punctuation marks, particularly commas and periods, indicating sentence structure and flow

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    sentence terminators

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Билгалдахарш
    -0.70
    
    -0.62
     AssemblyCompany
    -0.54
     typelib
    -0.50
    ьажоргаш
    -0.49
    RTGC
    -0.49
     мәкал
    -0.49
     للاسماء
    -0.47
    ьаж
    -0.46
     Савезне
    -0.46
    POSITIVE LOGITS
     tangki
    0.47
    retudo
    0.47
     chyba
    0.45
    /}.
    0.45
     wachten
    0.44
     Leith
    0.43
     cerah
    0.43
     Bescheid
    0.43
    ðsíða
    0.42
     Psych
    0.42
    Activations Density 0.086%

    No Known Activations