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. 22-GEMMASCOPE-RES-16K
    6. 12837
    Prev
    Next
    INDEX
    Explanations

    references to items or categories, particularly in a list or contextual framework

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    "Item" and variations

    np_acts-logits-general · gemini-2.0-flash

    item or Item identifiers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    GraphicsUnit
    -0.68
    AndPassword
    -0.66
    ViewImports
    -0.66
     GenerationType
    -0.64
    BagLayout
    -0.64
     otomatig
    -0.63
     Мексичка
    -0.59
    LayoutPanel
    -0.58
    informe
    -0.58
    ान्त
    -0.56
    POSITIVE LOGITS
     Items
    1.08
     items
    1.05
     ITEMS
    1.02
    items
    1.01
     Item
    0.92
     getItem
    0.91
     ITEM
    0.91
     newItem
    0.87
     item
    0.87
     itens
    0.82
    Activations Density 0.087%

    No Known Activations