© 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. 5-GEMMASCOPE-RES-16K
    6. 3620
    Prev
    Next
    INDEX
    Explanations

    references to illness and associated symptoms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    WithIdentifier
    -0.62
     credere
    -0.53
    AxisAlignment
    -0.52
    rael
    -0.51
    ggiamento
    -0.50
     BoxDecoration
    -0.49
     leef
    -0.49
    Бахар
    -0.49
     pageable
    -0.49
    WithFormat
    -0.48
    POSITIVE LOGITS
     sick
    1.89
    sick
    1.79
    Sick
    1.69
     Sick
    1.64
     sickness
    1.63
     SICK
    1.63
     Sickness
    1.49
     illness
    1.32
     Illness
    1.23
     illnesses
    1.23
    Activations Density 0.228%

    No Known Activations