© 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 - 16k
    9. 25-GEMMASCOPE-RES-16K
    11. 13093
    Prev
    Next
    INDEX
    Explanations

    HTML and JSX structural elements, indicating its focus on user interface components

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.hook_resid_post
    Hook Layer
    25
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     EconPapers
    -0.78
    出版年
    -0.72
     ProtoMessage
    -0.71
    GEBURTSDATUM
    -0.71
    انيف
    -0.67
    CloseOperation
    -0.63
     "<?
    -0.62
    complexContent
    -0.61
     AssemblyCulture
    -0.60
     Roskov
    -0.59
    POSITIVE LOGITS
     className
    1.29
    className
    0.98
     htmlFor
    0.79
    ClassName
    0.65
    ={
    0.63
     dangerously
    0.63
     key
    0.62
    key
    0.57
    {/*
    0.57
     classname
    0.53
    Activations Density 0.056%

    No Known Activations