Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 5090
    Prev
    Next
    INDEX
    Explanations

    terms related to human health risks associated with environmental factors and the promotion of health initiatives

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    fjspx
    -0.68
    GeneratedMessage
    -0.50
    PositiveButton
    -0.49
    뀜
    -0.48
    ulitan
    -0.47
     kaarangay
    -0.47
     Karp
    -0.47
     Dickerson
    -0.46
     KUMAR
    -0.46
     bağlantılar
    -0.46
    POSITIVE LOGITS
     health
    2.40
    health
    2.04
     Health
    1.86
     HEALTH
    1.83
    Health
    1.81
    HEALTH
    1.76
     santé
    1.67
     healthy
    1.57
    健康
    1.53
     salud
    1.53
    Activations Density 0.283%

    No Known Activations