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. 19-GEMMASCOPE-RES-16K
    6. 2002
    Prev
    Next
    INDEX
    Explanations

    specific formatting and layout properties in code snippets, particularly related to dimensions and positions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 19-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_19/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.19.hook_resid_post
    Hook Layer
    19
    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
    -0.65
    Jereo
    -0.51
    ItemBackground
    -0.50
    RegistryLite
    -0.50
    addCriterion
    -0.50
     geslacht
    -0.48
    RequestMapping
    -0.47
     paroisse
    -0.46
     факт
    -0.46
    iornamento
    -0.45
    POSITIVE LOGITS
    sizeCache
    0.67
    AnchorTagHelper
    0.64
     onCreateView
    0.60
    ună
    0.57
    ύπ
    0.55
     Kalyan
    0.55
    jsonwebtoken
    0.55
     CGSize
    0.54
    sizeof
    0.54
     Tôi
    0.53
    Activations Density 0.077%

    No Known Activations