© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 65k
    9. 20-GEMMASCOPE-RES-65K
    11. 1566
    Prev
    Next
    INDEX
    Explanations

    phrases indicating the need for medical attention or treatment

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

    urgent calls for medical intervention

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

    seeking professional assistance

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_65k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    MemoryWarning
    -0.90
    ChildScrollView
    -0.84
    TypedDataSet
    -0.81
    expandindo
    -0.80
    GEBURTSDATUM
    -0.78
     تضيفلها
    -0.74
    matchCondition
    -0.73
     magasiner
    -0.72
     Roskov
    -0.72
    Diwedd
    -0.71
    POSITIVE LOGITS
     help
    1.06
     assistance
    1.03
     Hilfe
    0.95
    help
    0.92
     ajutor
    0.87
    assistance
    0.86
     Help
    0.84
     hulp
    0.84
     professional
    0.82
    Help
    0.80
    Activations Density 0.085%

    No Known Activations