© 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-2-9B
    4. Residual Stream - 16k
    5. 31-GEMMASCOPE-RES-16K
    6. 2389
    Prev
    Next
    INDEX
    Explanations

    references to medical terms and terminology

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

    medical-related terminology and contexts.

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

    the word "medical" in various contexts.

    oai_token-act-pair · claude-4-5-haikuTriggered by @emiglarou
    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
     państw
    -0.38
     Farley
    -0.34
    shadowOpacity
    -0.34
    apin
    -0.32
    ESSOR
    -0.32
     cechy
    -0.32
    ittu
    -0.32
    empuan
    -0.32
     Bran
    -0.32
     hängen
    -0.32
    POSITIVE LOGITS
     المعيارى
    0.59
    SuspendLayout
    0.55
    Personensuche
    0.54
     ویکی‌پدی
    0.54
    NameInMap
    0.52
    HasAnnotation
    0.51
     noqa
    0.50
    bootstrapcdn
    0.50
     CanadaChoose
    0.50
    اریخ
    0.49
    Activations Density 0.144%

    No Known Activations