© 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 - 16k
    9. 24-GEMMASCOPE-RES-16K
    11. 8925
    Prev
    Next
    INDEX
    Explanations

    statistical associations related to stroke and cardiovascular health

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

    "OR" or "adjusted" related to odds ratio/hazard ratio calculations

    np_acts-logits-general · gemini-2.0-flash

    risk and association estimates

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ChildScrollView
    -0.60
     uuidv
    -0.56
     بيها
    -0.55
    kunde
    -0.51
    liel
    -0.50
    bruck
    -0.50
    נטי
    -0.49
    Aspect
    -0.49
    ็จ
    -0.49
    reus
    -0.48
    POSITIVE LOGITS
     adjusted
    0.84
     associations
    0.82
     risk
    0.82
     ajust
    0.73
     adjusting
    0.72
    risk
    0.71
    adjusted
    0.71
     association
    0.71
    justed
    0.69
    Associations
    0.69
    Activations Density 2.835%

    No Known Activations