© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 2-GEMMASCOPE-RES-16K
    11. 6853
    Prev
    Next
    INDEX
    Explanations

    references to the word "pur" in various contexts related to legal proceedings or petitions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_2/width_16k/average_l0_67
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Мексичка
    -0.60
     Numerade
    -0.57
     فريبيس
    -0.55
    AddAttribute
    -0.54
    LookAnd
    -0.54
     NSCoder
    -0.53
     Meksiku
    -0.51
    AndroidJUnit
    -0.49
    IsMutable
    -0.48
    MLLoader
    -0.48
    POSITIVE LOGITS
    Pur
    0.92
    pur
    0.87
     Pur
    0.82
     pursuit
    0.81
     pur
    0.81
     Pursuit
    0.78
     Bud
    0.76
    Bud
    0.76
     pursues
    0.75
     pursuing
    0.75
    Activations Density 0.487%

    No Known Activations