© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 131k
    9. 20-GEMMASCOPE-RES-131K
    11. 101089
    Prev
    Next
    INDEX
    Explanations

    terms related to death or dead states

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_131k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
    ítmény
    -0.54
    unile
    -0.54
    Figure
    -0.54
     Colby
    -0.53
    któ
    -0.52
     muestre
    -0.52
    stüt
    -0.51
     Figure
    -0.51
    Quinn
    -0.51
    cipation
    -0.50
    POSITIVE LOGITS
    Dead
    1.13
     Dead
    1.13
    dead
    1.07
     dead
    1.06
     DEAD
    1.04
    DEAD
    0.98
    isDead
    0.87
     deadlock
    0.70
    death
    0.63
     death
    0.62
    Activations Density 0.009%

    No Known Activations