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. 25-GEMMASCOPE-RES-16K
    6. 1420
    Prev
    Next
    INDEX
    Explanations

    components related to programming structures, particularly within graphical user interface elements

    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
    مصادر
    -0.64
    مراجع
    -0.51
    rawDesc
    -0.50
    BufferException
    -0.50
    RenderAtEndOf
    -0.48
    ніципалі
    -0.48
    useNewUrlParser
    -0.48
     DriverManager
    -0.48
    zule
    -0.47
    SpringBootTest
    -0.46
    POSITIVE LOGITS
    sortable
    0.68
     cell
    0.64
     sorting
    0.62
    nowrap
    0.61
    Cell
    0.60
     colspan
    0.58
     sorts
    0.57
     sorter
    0.56
     sor
    0.55
     TableColumn
    0.55
    Activations Density 0.145%

    No Known Activations