© 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. 4-GEMMASCOPE-RES-16K
    6. 1974
    Prev
    Next
    INDEX
    Explanations

    references to sugar and its effects or usage in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.hook_resid_post
    Hook Layer
    4
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    epam
    -0.84
    Personensuche
    -0.83
     defStyleAttr
    -0.71
     Rana
    -0.69
    "},
    -0.67
     depar
    -0.64
    "}},
    -0.63
     Sted
    -0.62
    }(),
    -0.62
    momile
    -0.61
    POSITIVE LOGITS
     sugar
    3.08
     Sugar
    2.77
    Sugar
    2.64
    sugar
    2.58
     SUGAR
    2.39
     sugars
    2.20
     azúcar
    1.75
    糖
    1.57
     sucre
    1.57
    UGAR
    1.56
    Activations Density 0.043%

    No Known Activations