© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 1-GEMMASCOPE-RES-16K
    6. 5891
    Prev
    Next
    INDEX
    Explanations

    references to opponents or adversarial relationships in the context of competition

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 1-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.1.hook_resid_post
    Hook Layer
    1
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     autorytatywna
    -0.85
     layui
    -0.78
    MLLoader
    -0.70
    Personensuche
    -0.64
     HasFactory
    -0.63
     balanceOf
    -0.62
    AccessorTable
    -0.62
    complexContent
    -0.62
     匿名
    -0.61
     kwiaty
    -0.60
    POSITIVE LOGITS
     opponent
    0.81
     opponents
    0.77
     Pal
    0.77
    pal
    0.67
    Pal
    0.64
    ochial
    0.63
    apal
    0.62
    ISCO
    0.61
     pal
    0.60
     "</
    0.60
    Activations Density 0.085%

    No Known Activations