© 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. 31-GEMMASCOPE-RES-16K
    11. 15139
    Prev
    Next
    INDEX
    Explanations

    references to assisted suicide and end-of-life decisions

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

    medical and health-related terminology, particularly around end-of-life care, euthanasia, and assisted suicide.

    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
    EFIAPI
    -0.43
    horabuena
    -0.43
    Toponymie
    -0.39
    garek
    -0.38
    Safety
    -0.38
     NSCoder
    -0.38
     publicidad
    -0.37
     malheureux
    -0.37
     república
    -0.37
    colazione
    -0.37
    POSITIVE LOGITS
     hospice
    1.23
     Hospice
    1.17
     palliative
    1.15
     Palli
    1.07
    Hosp
    1.01
     terminal
    0.90
     termin
    0.82
     palli
    0.80
     hosp
    0.78
     Terminal
    0.77
    Activations Density 0.217%

    No Known Activations