© 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. 14097
    Prev
    Next
    INDEX
    Explanations

    references to military forces and military actions

    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
     braccio
    -0.39
    ILON
    -0.35
     świad
    -0.35
    项目的
    -0.35
    getSystemService
    -0.34
    normalized
    -0.34
     programmet
    -0.34
     eksper
    -0.33
     spéciaux
    -0.33
     zdrow
    -0.33
    POSITIVE LOGITS
     retreating
    0.68
     flanks
    0.67
     offensi
    0.66
     offensive
    0.64
     retreat
    0.64
     tactical
    0.63
     evacuate
    0.63
     propOrder
    0.63
     demoral
    0.63
     advance
    0.62
    Activations Density 0.496%

    No Known Activations