© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 1502
    Prev
    Next
    INDEX
    Explanations

    references to legal concepts and beneficiary rights related to trusts and estates

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

    terms related to legal agreements and wills

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

    wills, estates, and trusts

    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
     صوتيه
    -0.68
    RegressionTest
    -0.61
     BorderRadius
    -0.60
     ویکی‌پدیای
    -0.60
     MainAxisSize
    -0.57
    AddHtmlAttribute
    -0.57
    ้อมูล
    -0.56
    uxxxx
    -0.55
     كومونز
    -0.54
     colorWith
    -0.53
    POSITIVE LOGITS
     wills
    1.38
     Wills
    1.12
     testamento
    1.07
     testament
    0.91
     estate
    0.90
     probate
    0.86
     willed
    0.84
     Estate
    0.84
     testa
    0.83
     trusts
    0.83
    Activations Density 0.207%

    No Known Activations