© 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. 105067
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "died."

    oai_token-act-pair · gpt-4o-miniTriggered 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
    Not in Any Lists

    No Comments

    Negative Logits
    havan
    -0.55
     Forster
    -0.55
    CFG
    -0.54
    Boulder
    -0.54
     Boulder
    -0.54
     Aurora
    -0.54
    RequestContext
    -0.53
     Cougar
    -0.53
     artig
    -0.53
     CFA
    -0.53
    POSITIVE LOGITS
    didSet
    0.72
    Dying
    0.63
    isDead
    0.59
    Décès
    0.58
     died
    0.57
     Dying
    0.57
     muerte
    0.56
    Died
    0.56
     Died
    0.55
    death
    0.54
    Activations Density 0.008%

    No Known Activations