© 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. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 10521
    Prev
    Next
    INDEX
    Explanations

    punctuation marks and their placement in sentences

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

    Punctuation at the end of a sentence

    np_acts-logits-general · gemini-2.0-flash

    sentence endings

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    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
     
    -0.93
     a
    -0.87
     in
    -0.86
     "
    -0.85
     and
    -0.84
     (
    -0.83
      
    -0.82
     or
    -0.82
     for
    -0.78
     on
    -0.77
    POSITIVE LOGITS
     שוליים
    1.32
     فريبيس
    1.25
    IsMutable
    1.18
     Audiodateien
    1.15
    __':
    1.12
     EconPapers
    1.11
     للاسماء
    1.11
     للمعارف
    1.11
     ویکی‌آمباردا
    1.10
     تانيه
    1.08
    Activations Density 0.186%

    No Known Activations