© 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. 1355
    Prev
    Next
    INDEX
    Explanations

    food-related terms or dishes

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

    Non-English language fragments and code snippets intermixed

    np_acts-logits-general · gemini-2.0-flash

    complex nouns and abbreviations

    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
     
    -0.62
     im
    -0.52
     j
    -0.50
     est
    -0.49
     for
    -0.49
     Re
    -0.47
    ון
    -0.47
     A
    -0.46
    Javadoc
    -0.46
     g
    -0.46
    POSITIVE LOGITS
     ſtate
    0.96
     myſelf
    0.92
     purpoſe
    0.89
     Jefus
    0.87
     ftate
    0.86
     ſmall
    0.85
    ſelf
    0.83
     houſe
    0.83
     ſever
    0.83
     perſon
    0.82
    Activations Density 0.031%

    No Known Activations