© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    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. 2542
    Prev
    Next
    INDEX
    Explanations

    references to medical professionals and institutions

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

    near medical locations and personnel

    np_acts-logits-general · gemini-2.0-flash

    emergency-room physician

    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
     Normdatei
    -0.52
     typelib
    -0.51
     חיצוניים
    -0.50
     שוליים
    -0.49
    MeasureSpec
    -0.49
     pouvoit
    -0.48
     étoit
    -0.48
    ✭✭
    -0.48
    žev
    -0.47
    acyjna
    -0.45
    POSITIVE LOGITS
     medical
    2.06
     doctors
    1.85
     Medical
    1.84
     hospital
    1.82
     hospitals
    1.76
     physicians
    1.75
    medical
    1.75
    Medical
    1.74
     physician
    1.72
     healthcare
    1.67
    Activations Density 1.988%

    No Known Activations