© 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. 11590
    Prev
    Next
    INDEX
    Explanations

    references to foundational concepts and theories, particularly in the context of Yang-Mills theories and related frameworks

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

    "Foundation" or "Yang" followed by specific words

    np_acts-logits-general · gemini-2.0-flash

    FoundationDB and Yang-Mills theory

    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
    ️
    -0.67
     naselje
    -0.64
    addContainerGap
    -0.64
     naturel
    -0.63
     تعدى
    -0.62
    ción
    -0.62
     Broncos
    -0.62
     rând
    -0.61
     plebis
    -0.61
     jouets
    -0.61
    POSITIVE LOGITS
    Spoljašnje
    0.64
    ContentAsync
    0.59
    什么
    0.57
    _{\
    0.56
     ttk
    0.55
    arily
    0.52
    Diweddarwch
    0.52
    ={`/
    0.51
    cetamol
    0.50
    انه
    0.49
    Activations Density 0.550%

    No Known Activations