© 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-2-2B
    4. Residual Stream - 16k
    5. 4-GEMMASCOPE-RES-16K
    6. 1696
    Prev
    Next
    INDEX
    Explanations

    terms related to medical symptoms and diagnoses

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.hook_resid_post
    Hook Layer
    4
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    aimana
    -0.81
    sizeCache
    -0.79
    orghini
    -0.73
    WriteBarrier
    -0.71
    mặt
    -0.71
    AntiForgeryToken
    -0.68
    Diweddarwch
    -0.67
    anskje
    -0.67
     שוליים
    -0.66
    agaimana
    -0.66
    POSITIVE LOGITS
     symptoms
    2.40
    symptoms
    2.01
     Symptoms
    1.98
     symptom
    1.96
    Symptoms
    1.93
     Symptom
    1.73
     síntomas
    1.45
     Symptome
    1.42
     symptômes
    1.42
     sintomas
    1.36
    Activations Density 0.182%

    No Known Activations