© 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. 31-GEMMASCOPE-RES-16K
    11. 14706
    Prev
    Next
    INDEX
    Explanations

    information about medical professionals and their qualifications

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

    detailed biographical information about medical professionals, particularly their educational and professional credentials.

    oai_token-act-pair · claude-3-5-haiku-20241022Triggered by @neilrathi

    educational and professional credentials in biographical or professional profiles.

    oai_token-act-pair · claude-4-5-haikuTriggered by @emiglarou

    professional biographical information, particularly educational credentials and career backgrounds of medical and healthcare professionals.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @jyhe0408

    biographical and profile passages detailing medical professionals’ credentials, specialties, education/training history, and institutional affiliations.

    oai_token-act-pair · gpt-5Triggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_31/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    posedge
    -0.69
     defaultstate
    -0.66
    rungsseite
    -0.64
     surla
    -0.62
    ChildScrollView
    -0.60
     '\\;'
    -0.59
    MessageTagHelper
    -0.59
    ImageContext
    -0.58
    StructEnd
    -0.58
     ujednoznacz
    -0.57
    POSITIVE LOGITS
     medical
    0.68
     clinical
    0.62
     Medical
    0.62
    Medical
    0.60
     MEDICAL
    0.59
    MEDICAL
    0.57
     Medizin
    0.54
    medical
    0.54
     médecine
    0.52
     Clinical
    0.52
    Activations Density 0.502%

    No Known Activations