© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 3-GEMMASCOPE-RES-16K
    6. 13596
    Prev
    Next
    INDEX
    Explanations

    references to legal cases and court proceedings related to an individual named Burton

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Baer
    -0.80
    csp
    -0.78
     Adi
    -0.75
     Foucault
    -0.73
     Gelb
    -0.72
    getElement
    -0.72
    djangoproject
    -0.72
    ͛
    -0.71
     Meksiku
    -0.70
     Levine
    -0.70
    POSITIVE LOGITS
    ','$
    0.87
    Lup
    0.85
     Lup
    0.84
    ✨:
    0.83
     Burton
    0.83
     Paran
    0.83
     Dearborn
    0.82
    pyplot
    0.82
     Dora
    0.81
     Felton
    0.80
    Activations Density 1.817%

    No Known Activations