© 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 - 16k
    9. 16-GEMMASCOPE-RES-16K
    11. 6946
    Prev
    Next
    INDEX
    Explanations

    confrontational language related to challenges or threats

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

    "challenge" or "duel"

    np_acts-logits-general · gemini-2.0-flash

    challenge or duel

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ScopeManager
    -0.61
    AccessorTable
    -0.57
    insegna
    -0.56
    SharedCtor
    -0.54
    AddHtmlAttribute
    -0.52
    kreis
    -0.52
    erschutz
    -0.52
     klucz
    -0.49
    effetto
    -0.49
     perkembangan
    -0.48
    POSITIVE LOGITS
     challenge
    0.97
    challenge
    0.85
     challenged
    0.84
    Challenge
    0.83
     Challenge
    0.82
     duel
    0.78
     challenger
    0.78
     CHALLENGE
    0.77
     challeng
    0.74
     desafi
    0.73
    Activations Density 0.212%

    No Known Activations