© 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. 143
    Prev
    Next
    INDEX
    Explanations

    medical case details, particularly related to patient history and surgical procedures

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

    information related to medical conditions and patient details

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

    female patient history

    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
     дописавши
    -0.81
    TabIndex
    -0.71
    انيف
    -0.69
    Either
    -0.69
    Παραπομπές
    -0.68
     Either
    -0.67
     textStatus
    -0.66
     entweder
    -0.66
     humaine
    -0.66
     humains
    -0.64
    POSITIVE LOGITS
     bilateral
    0.52
    ()]);
    0.50
    "]}
    0.50
    Agrade
    0.48
     she
    0.47
     left
    0.47
     right
    0.47
     Bauer
    0.47
     She
    0.47
     denies
    0.47
    Activations Density 0.748%

    No Known Activations