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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 9227
    Prev
    Next
    INDEX
    Explanations

    terms related to products and applications in industrial and mechanical contexts

    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
    
    -0.55
     versch
    -0.53
    xaml
    -0.53
    ardin
    -0.51
    zionalità
    -0.50
     porcelaine
    -0.48
    issima
    -0.47
    nom
    -0.47
     nắng
    -0.47
     còn
    -0.47
    POSITIVE LOGITS
    出版年
    0.86
     فريبيس
    0.68
    RenderAtEndOf
    0.66
    PyExc
    0.65
     snippetHide
    0.64
     ComVisible
    0.62
    MemoryWarning
    0.62
    MIDDLEWARE
    0.57
     виправивши
    0.56
     setPrice
    0.56
    Activations Density 0.670%

    No Known Activations