© 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. 10579
    Prev
    Next
    INDEX
    Explanations

    references to the term "bog" and various forms of the word "Boy" or associated encoding types

    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
     contextLoads
    -0.79
     betweenstory
    -0.68
     CURIAM
    -0.65
     Cæsar
    -0.65
    KommentareTeilen
    -0.64
    PHAN
    -0.64
     reaſon
    -0.63
    ILON
    -0.62
    formazioni
    -0.62
    
    -0.61
    POSITIVE LOGITS
     bog
    0.75
     Encoding
    0.69
     viewDidLoad
    0.67
    encoding
    0.66
    bog
    0.66
    Bog
    0.65
     encoding
    0.64
    пря
    0.61
    miro
    0.58
    sili
    0.55
    Activations Density 0.027%

    No Known Activations