© 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. 9019
    Prev
    Next
    INDEX
    Explanations

    references to mandates or obligations within legal texts

    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
    ínű
    -0.54
    Vik
    -0.49
    ViewStyle
    -0.48
    Vikt
    -0.48
    TopLeft
    -0.47
    outside
    -0.47
    Vicky
    -0.47
    Liz
    -0.47
     Vik
    -0.47
     Vicky
    -0.47
    POSITIVE LOGITS
     shall
    1.23
     Shall
    1.17
    shall
    1.09
    Shall
    1.06
     SHALL
    1.00
    jména
    0.72
     shalt
    0.69
    __.__
    0.66
    seamnă
    0.63
     fhall
    0.61
    Activations Density 0.134%

    No Known Activations