Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 9-GEMMASCOPE-RES-16K
    6. 720
    Prev
    Next
    INDEX
    Explanations

    mathematical notations and symbols related to complex equations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_9/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ‌هایی
    -0.60
    Dziękuję
    -0.59
     iconFacebook
    -0.59
    )])
    -0.57
     DEN
    -0.57
     Pelt
    -0.56
    BibitemShut
    -0.56
    >`;
    -0.56
    CodedInputStream
    -0.56
    '])
    
    -0.55
    POSITIVE LOGITS
    {
    1.11
    }{*}{
    0.95
    ={`/
    0.85
    DoubleQuotes
    0.85
    {~
    0.82
    #{
    0.81
     _("
    0.81
    !("{
    0.81
    ="{
    0.80
    ۜ
    0.79
    Activations Density 0.271%

    No Known Activations