© 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. 9123
    Prev
    Next
    INDEX
    Explanations

    language quantifying the quality of things, particularly using the terms "best" and "worst."

    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
     ویکی‌پدیای
    -0.80
    ViewFeatures
    -0.75
    SequentialGroup
    -0.74
    RenderAtEndOf
    -0.74
    twimg
    -0.73
    etcode
    -0.72
    weile
    -0.71
    exitRule
    -0.70
     Forumite
    -0.70
     commuters
    -0.69
    POSITIVE LOGITS
     best
    3.25
    best
    2.92
     BEST
    2.67
    Best
    2.65
     Best
    2.63
    BEST
    2.55
     terbaik
    1.89
     besten
    1.85
     beste
    1.77
     mejores
    1.74
    Activations Density 0.043%

    No Known Activations