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

    Neuronpedia

    Jacobian LensNEW
    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. 31-GEMMASCOPE-RES-16K
    11. 7284
    Prev
    Next
    INDEX
    Explanations

    legal terms and phrases related to document procedures and compliance

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

    legal and formal document language, particularly phrases related to court orders, document distribution, and official procedural instructions.

    oai_token-act-pair · claude-4-5-haikuTriggered by @emiglarou
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_31/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    一種
    -0.42
    asca
    -0.40
    一种
    -0.39
     Jackman
    -0.37
    ipot
    -0.37
    JoinColumn
    -0.36
    gamot
    -0.36
    uitable
    -0.35
    Filmografia
    -0.34
    แต่ง
    -0.34
    POSITIVE LOGITS
     copies
    2.86
     copy
    2.77
     Copies
    2.36
    copies
    2.28
     copie
    2.20
    copy
    2.19
     Copy
    2.19
    Copies
    2.17
    Copy
    2.00
     copia
    2.00
    Activations Density 0.488%

    No Known Activations