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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 10-GEMMASCOPE-RES-16K
    6. 11527
    Prev
    Next
    INDEX
    Explanations

    references to diseases and medical conditions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_10/width_16k/average_l0_113
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     StringTokenizer
    -0.63
    makeConstraints
    -0.56
     düğün
    -0.52
     bailarina
    -0.52
     Meksika
    -0.51
    yelidikan
    -0.51
     favoured
    -0.51
     Italij
    -0.49
     asunder
    -0.49
    AsNil
    -0.48
    POSITIVE LOGITS
     disease
    1.29
     Disease
    1.21
     illness
    1.14
    Disease
    1.14
    disease
    1.13
     sick
    1.11
     sickness
    1.11
     diseases
    1.09
     Illness
    1.05
     DISEASE
    1.04
    Activations Density 0.257%

    No Known Activations