© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 3911
    Prev
    Next
    INDEX
    Explanations

    technical terms and concepts related to advanced mathematical and physical theories, particularly in string theory and gauge theories

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

    Followed by physics/mathematical terms

    np_acts-logits-general · gemini-2.0-flash

    Yang-Mills theories

    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
     الحره
    -0.65
    曖昧さ回避
    -0.57
     crescere
    -0.51
    Décès
    -0.51
     Ngb
    -0.50
    AnimationsModule
    -0.50
     consultative
    -0.48
    <0xDA>
    -0.48
     Reverso
    -0.48
     murieron
    -0.48
    POSITIVE LOGITS
    isert
    0.53
     Scroll
    0.49
     string
    0.49
    PhysRevD
    0.49
     Wetter
    0.49
    Varint
    0.47
    quelize
    0.47
    tiftung
    0.46
    ecap
    0.45
    stree
    0.45
    Activations Density 1.774%

    No Known Activations