© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 1743
    Prev
    Next
    INDEX
    Explanations

    references to medical test results and patient demographics, particularly related to conversions and condition classifications

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

    versus or compared to

    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
     utafitiHapana
    -0.85
     CreateTagHelper
    -0.74
     Мексичка
    -0.73
     تضيفلها
    -0.70
    JspWriter
    -0.70
    RegistryLite
    -0.69
    ddots
    -0.68
    )))));
    -0.66
    DoubleQuotes
    -0.66
     gainera
    -0.65
    POSITIVE LOGITS
     vs
    4.03
     versus
    3.92
    versus
    3.08
     Versus
    3.07
     Vs
    3.03
    vs
    2.88
     VS
    2.67
    Versus
    2.48
     compared
    2.33
    VS
    2.00
    Activations Density 1.214%

    No Known Activations