© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 34-GEMMASCOPE-RES-16K
    11. 7069
    Prev
    Next
    INDEX
    Explanations

    references to tragic events and memorials

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 34-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_34/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.34.hook_resid_post
    Hook Layer
    34
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    mittags
    -0.38
     demografica
    -0.37
    riwal
    -0.37
     nachher
    -0.37
    相変わらず
    -0.36
     definiciones
    -0.35
     Aufenthalt
    -0.35
     geschickt
    -0.35
     verteilt
    -0.35
     cintura
    -0.35
    POSITIVE LOGITS
     deceased
    0.98
     tragically
    0.97
     murdered
    0.91
     tragic
    0.90
     slain
    0.89
     perished
    0.84
     died
    0.84
     beloved
    0.83
     killed
    0.82
    Trag
    0.81
    Activations Density 0.256%

    No Known Activations