© 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. 33-GEMMASCOPE-RES-16K
    11. 12769
    Prev
    Next
    INDEX
    Explanations

    legal terminology and references related to citizenship and immigration

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 33-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_33/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.33.hook_resid_post
    Hook Layer
    33
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     allons
    -0.38
     unethical
    -0.37
    atko
    -0.36
    arrête
    -0.35
     timelines
    -0.35
     рекомендуется
    -0.35
     conseille
    -0.34
    蚪
    -0.34
    babkan
    -0.33
     "..\..\..\
    -0.33
    POSITIVE LOGITS
     Congress
    0.59
    IGraphics
    0.50
    addContainerGap
    0.49
    BagLayout
    0.48
     congress
    0.48
     initComponents
    0.48
    AddTagHelper
    0.48
    سطس
    0.48
     CONGRESS
    0.48
     congressional
    0.48
    Activations Density 3.674%

    No Known Activations