© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 30-GEMMASCOPE-RES-16K
    11. 10658
    Prev
    Next
    INDEX
    Explanations

    references to medical professionals and their roles

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

    medicine or doctors

    np_acts-logits-general · gemini-2.0-flash

    physicians and doctors

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 30-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_30/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.30.hook_resid_post
    Hook Layer
    30
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    openConnection
    -0.54
    ConstraintMaker
    -0.51
     typelib
    -0.51
    WriteBarrier
    -0.49
     يتيمه
    -0.46
     للاسماء
    -0.44
     utafitiHapana
    -0.43
     Italijanski
    -0.42
    oa̍t
    -0.41
    tinyos
    -0.41
    POSITIVE LOGITS
     medical
    1.84
     doctors
    1.71
     physicians
    1.63
     Medical
    1.62
     hospital
    1.60
    Medical
    1.59
    medical
    1.59
     hospitals
    1.57
     médicos
    1.50
     medically
    1.48
    Activations Density 1.435%

    No Known Activations