© 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. 38-GEMMASCOPE-RES-16K
    11. 15660
    Prev
    Next
    INDEX
    Explanations

    details related to mortality, causes of death, and associated circumstances

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 38-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_38/width_16k/average_l0_128
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.38.hook_resid_post
    Hook Layer
    38
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     murdered
    -0.63
     Killed
    -0.58
    لينكات
    -0.57
     slain
    -0.53
     assassinated
    -0.51
     للاسماء
    -0.50
     ChromeDriver
    -0.50
     fainted
    -0.50
     slaughtered
    -0.49
     wounded
    -0.48
    POSITIVE LOGITS
     death
    1.91
    death
    1.52
    Death
    1.30
     Death
    1.30
     DEATH
    1.27
     muerte
    1.20
    DEATH
    1.11
     deaths
    0.94
     kematian
    0.90
     смерть
    0.90
    Activations Density 0.463%

    No Known Activations