© 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-2-9B-IT
    7. Residual Stream - 131k
    9. 20-GEMMASCOPE-RES-131K
    11. 80123
    Prev
    Next
    INDEX
    Explanations

    references to individuals or populations that are categorized by health status, age, or demographic vulnerability

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

    health status of individuals

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    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
    SequentialGroup
    -0.69
    DotNetBar
    -0.68
    aarrggbb
    -0.68
    GEBURTSDATUM
    -0.62
    httphttps
    -0.61
    artifactId
    -0.59
     intptr
    -0.59
    reactstrap
    -0.59
     nahilalakip
    -0.58
    msgTypes
    -0.58
    POSITIVE LOGITS
     young
    0.57
     students
    0.56
     individuals
    0.47
     people
    0.46
     fellow
    0.44
    young
    0.43
     jungen
    0.43
     student
    0.43
     jonge
    0.41
     clients
    0.40
    Activations Density 0.132%

    No Known Activations