© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 41-GEMMASCOPE-RES-16K
    11. 7503
    Prev
    Next
    INDEX
    Explanations

    events involving conflicts or military actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 41-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_41/width_16k/average_l0_113
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.41.hook_resid_post
    Hook Layer
    41
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    fights
    -0.54
     Bombs
    -0.52
    :✨
    -0.51
     للمعارف
    -0.50
    pushFollow
    -0.49
     fights
    -0.46
     Fires
    -0.45
    
    -0.45
     linkovi
    -0.45
    kämp
    -0.45
    POSITIVE LOGITS
     raid
    0.54
     operation
    0.53
     coordinated
    0.52
     unsuccessful
    0.46
     offensive
    0.46
     daring
    0.46
     attack
    0.45
     daylight
    0.45
     blitz
    0.43
     blit
    0.42
    Activations Density 0.483%

    No Known Activations