© 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 - 65k
    9. 20-GEMMASCOPE-RES-65K
    11. 129
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions involving inequalities and equations

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

    mathematical expressions and equations

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

    numbers and arithmetic

    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-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_65k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    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
     defaultstate
    -0.72
    writeField
    -0.54
    Pautan
    -0.54
     وتسجيلات
    -0.50
    InjectAttribute
    -0.49
    Geplaatst
    -0.47
     оригіналу
    -0.46
     pageable
    -0.46
    testify
    -0.46
     linkovi
    -0.46
    POSITIVE LOGITS
     twice
    1.02
     two
    0.93
     deux
    0.93
    twice
    0.92
     thrice
    0.85
     두
    0.83
     Twice
    0.82
     three
    0.81
    Twice
    0.80
     TWO
    0.78
    Activations Density 0.922%

    No Known Activations