© 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-2-9B
    7. Residual Stream - 16k
    9. 33-GEMMASCOPE-RES-16K
    11. 8130
    Prev
    Next
    INDEX
    Explanations

    references to nuclear weapons and military threats

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 33-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_33/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.33.hook_resid_post
    Hook Layer
    33
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Frey
    -0.40
     galletas
    -0.37
     recuperação
    -0.36
     temporaire
    -0.34
     recovering
    -0.34
    Copa
    -0.34
    Temporary
    -0.34
     temporary
    -0.34
     Temporary
    -0.33
     Polres
    -0.32
    POSITIVE LOGITS
     nuclear
    1.35
    nuclear
    1.17
    Nuclear
    1.14
     Nuclear
    1.13
     nukes
    1.13
     NUCLEAR
    0.99
     atomic
    0.98
     nuke
    0.96
     nucléaire
    0.95
    核
    0.91
    Activations Density 0.250%

    No Known Activations