© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 16-GEMMASCOPE-RES-16K
    11. 11491
    Prev
    Next
    INDEX
    Explanations

    references to palliative and end-of-life care

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

    End-of-life and palliative care

    np_acts-logits-general · gemini-2.0-flash

    palliative care and end of life

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    存于互联网档案馆
    -0.51
    minipage
    -0.50
    INLINE
    -0.49
    vención
    -0.47
    Caro
    -0.46
     Piran
    -0.45
     scom
    -0.45
     Dwight
    -0.44
    devil
    -0.44
    ldorf
    -0.44
    POSITIVE LOGITS
     Hospice
    1.32
     hospice
    1.21
     palliative
    1.15
    Hosp
    0.99
     Palli
    0.94
     death
    0.85
     dying
    0.79
     Death
    0.78
    MigrationBuilder
    0.76
    death
    0.75
    Activations Density 0.295%

    No Known Activations