© 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-2-2B
    7. Residual Stream - 16k
    9. 11-GEMMASCOPE-RES-16K
    11. 2627
    Prev
    Next
    INDEX
    Explanations

    references to death or dead entities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Hook Layer
    11
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    kkor
    -0.93
    깐
    -0.89
    ябре
    -0.88
     betreft
    -0.87
    évaluateur
    -0.86
     unknownFields
    -0.83
    könyv
    -0.83
    脚注の使い方
    -0.83
    uride
    -0.82
    lgari
    -0.82
    POSITIVE LOGITS
     Dead
    1.62
     dead
    1.61
    Dead
    1.54
     DEAD
    1.50
    dead
    1.39
    DEAD
    1.22
    死
    0.90
     Toten
    0.86
     mort
    0.81
    isDead
    0.81
    Activations Density 0.071%

    No Known Activations