© 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. 14046
    Prev
    Next
    INDEX
    Explanations

    incidents related to explosions or destructive events

    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
    Ligações
    -0.37
    偷偷
    -0.34
     Zen
    -0.33
    悄悄
    -0.33
     accordé
    -0.32
    angebot
    -0.32
    convite
    -0.32
    weilen
    -0.31
    Application
    -0.31
     envie
    -0.30
    POSITIVE LOGITS
     shattered
    0.79
     shattering
    0.77
     splat
    0.73
     mangled
    0.73
     debris
    0.73
    splat
    0.71
     wreckage
    0.71
     splin
    0.71
     rico
    0.69
     violently
    0.69
    Activations Density 0.454%

    No Known Activations