© 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. 2774
    Prev
    Next
    INDEX
    Explanations

    legal terminology and concepts related to judicial proceedings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    legal and judicial terminology and concepts.

    oai_token-act-pair · claude-3-5-haiku-20241022Triggered by @neilrathi
    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
     her
    -0.37
     full
    -0.34
    Priority
    -0.31
     stuffed
    -0.31
     Shelf
    -0.30
    PRIORITY
    -0.29
     Full
    -0.29
    Full
    -0.28
    Hierarchy
    -0.28
     shelf
    -0.28
    POSITIVE LOGITS
    RenderAtEndOf
    0.76
     <<<<<<<<<<<<<<
    0.75
    IndentedString
    0.70
    ⟬
    0.67
    MemoryWarning
    0.66
     legitimate
    0.65
     naturali
    0.60
    HasAnnotation
    0.60
     légitime
    0.60
    parsedMessage
    0.59
    Activations Density 0.385%

    No Known Activations