© 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. 0-GEMMASCOPE-RES-65K
    11. 9857
    Prev
    Next
    INDEX
    Explanations

    references to causes of medical conditions and diseases

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 0-gemmascope-res-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_0/width_65k/average_l0_73
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    Data Type
    float32
    Hook Name
    blocks.0.hook_resid_post
    Hook Layer
    0
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    AccessorTable
    -0.88
    AndEndTag
    -0.79
     JpaRepository
    -0.77
    SBATCH
    -0.72
    تقاوى
    -0.72
     وتسجيلات
    -0.71
    SharedDtor
    -0.70
     Efq
    -0.69
     autorytatywna
    -0.69
    Hentet
    -0.66
    POSITIVE LOGITS
    行
    0.73
    Caus
    0.68
     Caus
    0.66
    多
    0.65
     Kos
    0.64
     Cassie
    0.60
     caustic
    0.59
     almost
    0.58
    Authentic
    0.57
    Kos
    0.56
    Activations Density 0.056%

    No Known Activations