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. 20-GEMMASCOPE-RES-16K
    6. 11879
    Prev
    Next
    INDEX
    Explanations

    terms related to patients and their care or safety

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    "patient" and related terms

    np_acts-logits-general · gemini-2.0-flash

    patient demographics satisfaction care safety management

    np_acts-logits-general · gemini-2.5-flash-lite
    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
    InputBorder
    -1.15
     EconPapers
    -1.06
    XmlAccessType
    -0.98
    AsUp
    -0.98
     تضيفلها
    -0.91
    MethodManager
    -0.90
    bootstrapcdn
    -0.87
     defaultstate
    -0.87
     فريبيس
    -0.86
     ویکی‌پدی
    -0.85
    POSITIVE LOGITS
     Patients
    0.89
     patients
    0.89
    Patients
    0.81
    patients
    0.79
    <h6>
    0.62
     Pati
    0.60
     pati
    0.59
     Patient
    0.58
     patient
    0.57
     환
    0.56
    Activations Density 0.118%

    No Known Activations