© 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-2-9B
    7. Residual Stream - 16k
    9. 31-GEMMASCOPE-RES-16K
    11. 10613
    Prev
    Next
    INDEX
    Explanations

    references to health issues and illnesses, particularly in a terminal context

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

    phrases about serious illness, medical conditions, and health challenges.

    oai_token-act-pair · claude-3-5-haiku-20241022Triggered by @neilrathi

    words and phrases related to serious illness, terminal conditions, and death.

    oai_token-act-pair · claude-4-5-haikuTriggered by @emiglarou
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_31/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    webElementXpaths
    -0.35
    enumi
    -0.32
    entlich
    -0.29
    WriteBarrier
    -0.26
    unduh
    -0.26
     atrás
    -0.25
    isNameExpr
    -0.24
     اجتما
    -0.24
     Pontific
    -0.24
     arran
    -0.24
    POSITIVE LOGITS
     sick
    1.86
     illness
    1.85
     sickness
    1.73
    sick
    1.68
     Illness
    1.61
     illnesses
    1.58
    Sick
    1.46
     malade
    1.45
     unwell
    1.43
    生病
    1.43
    Activations Density 0.259%

    No Known Activations