© 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-2-2B
    7. Residual Stream - 16k
    9. 24-GEMMASCOPE-RES-16K
    11. 6778
    Prev
    Next
    INDEX
    Explanations

    events related to death and passing away

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

    death or passing

    np_acts-logits-general · gemini-2.0-flash

    passing away peacefully

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ستین
    -0.58
     كمان
    -0.57
    proken
    -0.56
     kapag
    -0.55
    每一次
    -0.55
     Allerdings
    -0.54
    Moreover
    -0.54
    ってみる
    -0.53
    cookieParser
    -0.53
    inguém
    -0.53
    POSITIVE LOGITS
     surrounded
    1.24
     peacefully
    1.12
     entour
    1.05
     rodeado
    0.84
     surround
    0.82
     unexpectedly
    0.77
    sur
    0.77
     due
    0.71
     comforted
    0.70
     after
    0.69
    Activations Density 0.030%

    No Known Activations