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. 17-GEMMASCOPE-RES-16K
    6. 5794
    Prev
    Next
    INDEX
    Explanations

    mathematical symbols and notations related to definitions and properties in algebra

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 17-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_17/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.17.hook_resid_post
    Hook Layer
    17
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    didSet
    -0.48
    ganie
    -0.48
    veranstal
    -0.46
    getSystemService
    -0.45
    naden
    -0.45
     credible
    -0.44
     lateinit
    -0.43
    plor
    -0.43
    \}^{
    -0.43
     giác
    -0.43
    POSITIVE LOGITS
     AspNetCore
    0.91
     betweenstory
    0.88
     متعلقه
    0.82
     Administrativna
    0.78
    GEBURTSDATUM
    0.78
     незавершена
    0.77
     للمعارف
    0.75
     kaarangay
    0.75
     '\\;'
    0.74
     XCTest
    0.73
    Activations Density 2.703%

    No Known Activations