© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 65k
    9. 0-GEMMASCOPE-RES-65K
    11. 10214
    Prev
    Next
    INDEX
    Explanations

    references to social classes and class distinctions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 0-gemmascope-res-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_0/width_65k/average_l0_73
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    Data Type
    float32
    Hook Name
    blocks.0.hook_resid_post
    Hook Layer
    0
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ----</
    -0.80
    rungsseite
    -0.78
    esterday
    -0.77
    ceutical
    -0.76
    ratulations
    -0.74
    værende
    -0.73
    iented
    -0.73
    didSet
    -0.69
    ordinaire
    -0.69
    eryllium
    -0.68
    POSITIVE LOGITS
     Class
    1.67
    Class
    1.60
     class
    1.47
     classes
    1.45
     CLASS
    1.39
     Classes
    1.38
    class
    1.20
    CLASS
    1.20
    Classes
    1.20
    classes
    1.13
    Activations Density 0.052%

    No Known Activations