© 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. 3734
    Prev
    Next
    INDEX
    Explanations

    punctuation marks and sentence relevance within the text

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

    Sentences following a period

    np_acts-logits-general · gemini-2.0-flash

    sentence beginnings after punctuation

    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
     صوتيه
    -0.76
     Normdatei
    -0.71
    Sinon
    -0.65
    кож
    -0.65
     plz
    -0.64
     Ferner
    -0.64
     ExecuteAsync
    -0.63
     ALSO
    -0.61
    versaire
    -0.60
     Daarna
    -0.58
    POSITIVE LOGITS
     Ajoutez
    0.82
     Enter
    0.78
     Add
    0.77
    Enter
    0.75
     even
    0.75
    Nowhere
    0.74
     add
    0.71
    だからこそ
    0.70
     enter
    0.70
    Add
    0.68
    Activations Density 0.255%

    No Known Activations