© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 105516
    Prev
    Next
    INDEX
    Explanations

    references to the concept of legitimacy or lawful authority

    oai_token-act-pair · gpt-4o-mini
    Triggered 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
    Negative Logits
     Spray
    -0.50
     Russland
    -0.48
     Painter
    -0.48
     Milán
    -0.47
     spray
    -0.47
    Spray
    -0.46
     Rusia
    -0.46
     París
    -0.45
     Spider
    -0.44
     Byers
    -0.44
    POSITIVE LOGITS
    itimate
    1.16
     legitimate
    0.99
     Legit
    0.90
     legitim
    0.83
     legit
    0.80
     legitimacy
    0.77
     legiti
    0.76
     illegitimate
    0.74
     legitimately
    0.71
    Legit
    0.69
    Activations Density 0.009%

    No Known Activations