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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 15275
    Prev
    Next
    INDEX
    Explanations

    legal terminology related to authority and power

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_16k/average_l0_68
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    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
    separ
    -0.40
     lip
    -0.38
     sobbed
    -0.35
    clown
    -0.34
     puffy
    -0.34
     convi
    -0.34
     chunky
    -0.33
    Tau
    -0.33
    aktery
    -0.33
    床上
    -0.33
    POSITIVE LOGITS
     poderes
    0.54
     autoridad
    0.50
    addGap
    0.49
     authorisation
    0.48
     authority
    0.47
     authorised
    0.47
     ModelExpression
    0.47
    encodeWith
    0.47
     powers
    0.47
     ]}
    0.46
    Activations Density 0.434%

    No Known Activations