© 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 - 131k
    9. 20-GEMMASCOPE-RES-131K
    11. 105809
    Prev
    Next
    INDEX
    Explanations

    references to military and combat-related themes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_131k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     invokingState
    -0.51
     &___
    -0.49
     betweenstory
    -0.49
    日閲覧
    -0.49
    djangoproject
    -0.48
     Савезне
    -0.48
    RegistryLite
    -0.47
    
    -0.47
     tatuagem
    -0.46
     rehabilitación
    -0.45
    POSITIVE LOGITS
     counter
    0.49
     Counter
    0.43
    counter
    0.42
     support
    0.41
    Counter
    0.40
    support
    0.37
     quota
    0.37
     battle
    0.37
     COE
    0.37
     Vigil
    0.37
    Activations Density 0.109%

    No Known Activations