© 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. 10-GEMMASCOPE-RES-16K
    6. 13041
    Prev
    Next
    INDEX
    Explanations

    terms related to health and wellness

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     SqlCommand
    -0.71
     kasarigan
    -0.68
     חיצוניים
    -0.66
    섰
    -0.64
     références
    -0.63
     pudesse
    -0.63
     hefyd
    -0.63
     climá
    -0.62
    gså
    -0.61
     tivesse
    -0.61
    POSITIVE LOGITS
     healthy
    1.27
    healthy
    1.20
     Healthy
    1.20
    Healthy
    1.17
    olesome
    1.01
     unhealthy
    0.94
     saludable
    0.92
    )";
    
    0.91
     saudável
    0.88
    '>";
    0.87
    Activations Density 0.072%

    No Known Activations