© 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. 3-GEMMASCOPE-RES-16K
    11. 16030
    Prev
    Next
    INDEX
    Explanations

    references to diseases and related medical conditions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     étoit
    -0.77
     AssemblyCulture
    -0.74
     auroit
    -0.73
     chré
    -0.71
     étoient
    -0.69
     avoient
    -0.69
     démocr
    -0.68
     nôtre
    -0.68
     pouvoit
    -0.67
     Sheryl
    -0.66
    POSITIVE LOGITS
     disease
    2.97
     Disease
    2.68
     diseases
    2.55
    Disease
    2.41
    disease
    2.40
     DISEASE
    2.40
     Diseases
    2.26
    Diseases
    2.07
     DISEASES
    2.01
    diseases
    1.88
    Activations Density 0.139%

    No Known Activations