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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 17-GEMMASCOPE-RES-16K
    6. 6023
    Prev
    Next
    INDEX
    Explanations

    elements related to medical conditions and health issues, particularly focusing on cardiovascular health

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 17-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_17/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.17.hook_resid_post
    Hook Layer
    17
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    بالإنجليزية
    -0.52
     mauvais
    -0.47
     surla
    -0.47
    inste
    -0.47
     /
    -0.46
     trotzdem
    -0.46
    ortunadamente
    -0.45
     susceptibles
    -0.45
    penup
    -0.44
     diye
    -0.44
    POSITIVE LOGITS
     }}$}
    0.90
    ^(@)
    0.84
    ✨:
    0.80
     ―――――
    0.80
     Efq
    0.79
    )");
    
    0.79
    不但
    0.77
     ་་
    0.74
    oredCriteria
    0.73
    ſelf
    0.73
    Activations Density 0.419%

    No Known Activations