© 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. 3572
    Prev
    Next
    INDEX
    Explanations

    references to nuclear weapons and the associated threats

    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
     galletas
    -0.40
     blazed
    -0.34
    Copa
    -0.32
     Frey
    -0.32
    Géographie
    -0.32
     temporaire
    -0.32
     recuperação
    -0.31
     Henne
    -0.30
    τώ
    -0.30
     recupero
    -0.30
    POSITIVE LOGITS
     nuclear
    1.30
     nukes
    1.13
    nuclear
    1.11
     Nuclear
    1.06
    Nuclear
    1.06
     NUCLEAR
    0.96
     nuke
    0.94
    核
    0.90
     nucléaire
    0.88
     missile
    0.86
    Activations Density 0.264%

    No Known Activations