© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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 - 16k
    9. 15-GEMMASCOPE-RES-16K
    11. 7095
    Prev
    Next
    INDEX
    Explanations

    specific descriptions of physical attributes and colors

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_15/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    complexContent
    -0.86
     disambiguazione
    -0.85
     TextAppearance
    -0.74
     Italijani
    -0.73
    httphttps
    -0.69
    ItemBackground
    -0.68
    发表于
    -0.68
    oredCriteria
    -0.65
    verwijspagina
    -0.65
     autorytatywna
    -0.63
    POSITIVE LOGITS
    下载附件
    0.61
    ViewInit
    0.60
    reportWebVitals
    0.54
    PerformLayout
    0.53
    AfterViewInit
    0.53
    adaptiveStyles
    0.51
    useNewUrlParser
    0.48
    StandardCharsets
    0.47
    !*\
    0.46
     Enfin
    0.45
    Activations Density 0.862%

    No Known Activations