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

    Neuronpedia

    Jacobian LensNEW
    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. 15090
    Prev
    Next
    INDEX
    Explanations

    specific medical conditions and related diagnostic terms

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

    medical terminology related to health conditions, diagnostic procedures, and patient symptoms, with a particular focus on lung and respiratory-related medical details.

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

    medical and clinical terminology in academic or technical documents.

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

    medical case reports and clinical documentation, particularly diagnostic procedures and patient histories.

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

    technical clinical case-report language about respiratory conditions, especially detailing symptoms, imaging-based diagnosis, and surgical management

    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
     pinulongan
    -0.76
     Houſe
    -0.62
    ConstraintMaker
    -0.54
     cancerous
    -0.52
    bibfield
    -0.51
    vability
    -0.50
    zheim
    -0.49
     Majefty
    -0.49
    SequentialGroup
    -0.49
    WriteBarrier
    -0.49
    POSITIVE LOGITS
     physiologic
    0.73
     patients
    0.65
     clinically
    0.62
     Patients
    0.59
     clinical
    0.58
     patient
    0.57
     clinicians
    0.56
     Clinical
    0.56
    ologic
    0.55
    Patients
    0.54
    Activations Density 7.668%

    No Known Activations