© 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
    7. Residual Stream - 16k
    9. 36-GEMMASCOPE-RES-16K
    11. 12331
    Prev
    Next
    INDEX
    Explanations

    references to health and welfare issues, particularly concerning individuals and marginalized groups

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 36-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_36/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.36.hook_resid_post
    Hook Layer
    36
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    makeConstraints
    -0.46
     initComponents
    -0.45
    RTHOOK
    -0.43
     Obrador
    -0.42
    layoutControl
    -0.42
    initComponents
    -0.42
    RefNanny
    -0.40
    CreateModel
    -0.40
    reactstrap
    -0.39
    ributo
    -0.39
    POSITIVE LOGITS
     welfare
    1.57
     wellbeing
    1.54
     bienestar
    1.26
     health
    1.25
    welfare
    1.24
     WELFARE
    1.09
     safety
    1.05
     Welfare
    1.02
     benessere
    1.02
    health
    1.00
    Activations Density 0.579%

    No Known Activations