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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 70664
    Prev
    Next
    INDEX
    Explanations

    terms related to object attributes in programming, specifically in Android layout design

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_131k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    rawDesc
    -0.72
    BindingResult
    -0.52
     nakalista
    -0.42
     completos
    -0.37
     הור
    -0.37
     Lös
    -0.35
     vérit
    -0.35
    setModel
    -0.35
     Úl
    -0.34
     asesinato
    -0.34
    POSITIVE LOGITS
    ItemBackground
    2.39
     становника
    2.22
    ParseTree
    1.52
    sizeCache
    1.51
    expandindo
    1.39
    ThemeOverlay
    1.34
     initComponents
    1.23
     stanovnika
    1.10
    gonic
    0.98
    ValueStyle
    0.85
    Activations Density 0.000%

    No Known Activations