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

    Neuronpedia

    Jacobian LensNEW
    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. 18-GEMMASCOPE-RES-16K
    11. 15693
    Prev
    Next
    INDEX
    Explanations

    discussions regarding responsibility and blame in various contexts

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

    before "responsibility" or "burden"

    np_acts-logits-general · gemini-2.0-flash

    responsibility and burden

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     JpaRepository
    -0.62
     ویکی‌پدیای
    -0.61
    ᅠ
    -0.59
     Roskov
    -0.52
     Knie
    -0.50
    testcase
    -0.49
     elkaar
    -0.49
    Билгалдахарш
    -0.48
     nahilalakip
    -0.46
    +/**
    -0.45
    POSITIVE LOGITS
     belongs
    1.39
     belong
    1.39
     belonged
    1.35
    belong
    1.17
    belongs
    1.09
     appartient
    0.97
     apparti
    0.93
     belonging
    0.90
     responsibility
    0.90
     appartiennent
    0.89
    Activations Density 0.266%

    No Known Activations