© 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. 6111
    Prev
    Next
    INDEX
    Explanations

    legal terms and administrative processes related to court rulings

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

    legal document language and judicial procedure terms, particularly related to court orders, directives, and instructions.

    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
    kå
    -0.35
    finally
    -0.34
     onView
    -0.34
    Решение
    -0.34
    PhysRevLett
    -0.33
    ELTS
    -0.33
     contextLoads
    -0.33
    cshtml
    -0.32
     Manta
    -0.31
    󠁮
    -0.31
    POSITIVE LOGITS
     ModelRenderer
    0.56
     EconPapers
    0.54
    prefixer
    0.53
     FetchType
    0.52
     Chwiliwch
    0.51
     please
    0.50
     ModelExpression
    0.48
     mögen
    0.47
     ComVisible
    0.47
    please
    0.47
    Activations Density 0.188%

    No Known Activations