© 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. 11-GEMMASCOPE-RES-16K
    11. 8620
    Prev
    Next
    INDEX
    Explanations

    references to legal terms and court documentation, particularly those related to the Ninth Circuit

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 11-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_11/width_16k/average_l0_118
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Hook Layer
    11
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Ivoire
    -0.54
     gynhyrchwyd
    -0.51
    mmate
    -0.50
    createClass
    -0.50
    oader
    -0.50
     createSprite
    -0.50
    usercontent
    -0.49
    libc
    -0.48
    ditor
    -0.48
    camper
    -0.47
    POSITIVE LOGITS
    9
    1.32
     nine
    1.05
     Nine
    1.03
     Ninth
    0.92
    Nine
    0.90
     ninth
    0.90
     NINE
    0.88
    nine
    0.88
     nueve
    0.86
     девя
    0.84
    Activations Density 0.586%

    No Known Activations