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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 65k
    5. 13-GEMMASCOPE-RES-65K
    6. 15674
    Prev
    Next
    INDEX
    Explanations

    topics related to health services and healthcare research

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 13-gemmascope-res-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_13/width_65k/average_l0_75
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    Data Type
    float32
    Hook Name
    blocks.13.hook_resid_post
    Hook Layer
    13
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    IDADE
    -0.59
     تانيه
    -0.53
    boe
    -0.50
     réus
    -0.50
     one
    -0.50
    Void
    -0.48
    velse
    -0.48
     chi̍t
    -0.48
    曖昧さ回避
    -0.47
    ultado
    -0.47
    POSITIVE LOGITS
     respectively
    0.88
    respectively
    0.81
    IntoConstraints
    0.79
     alike
    0.76
     respectivamente
    0.71
     kasarigan
    0.65
     StatefulWidget
    0.59
     cherchés
    0.59
    DJANGO
    0.59
     فريبيس
    0.58
    Activations Density 0.257%

    No Known Activations