© 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. 20-GEMMASCOPE-RES-16K
    11. 8063
    Prev
    Next
    INDEX
    Explanations

    references to laws and legal statutes

    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
     Grüsse
    -0.54
    Inside
    -0.51
     Suresh
    -0.49
    Gente
    -0.47
    Excellent
    -0.46
    parsedMessage
    -0.46
    Spare
    -0.46
    peti
    -0.46
    Mit
    -0.46
     Guildford
    -0.45
    POSITIVE LOGITS
     law
    1.03
     laws
    1.02
     Laws
    0.96
     Law
    0.88
     LAWS
    0.83
     LAW
    0.83
    Laws
    0.82
     legislation
    0.80
     Gesetz
    0.80
     statute
    0.74
    Activations Density 0.232%

    No Known Activations