© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    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. 3729
    Prev
    Next
    INDEX
    Explanations

    HTML-like tags and structures related to items and values in a data context

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

    Tokens preceding "item" or "Item"

    np_acts-logits-general · gemini-2.0-flash

    list items

    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
     '\\;'
    -0.81
    IndentedString
    -0.71
    TemporalType
    -0.67
    SharedDtor
    -0.65
    GeneratedCode
    -0.65
    retario
    -0.63
    Попис
    -0.62
    PMailer
    -0.61
    complexContent
    -0.61
    ranet
    -0.61
    POSITIVE LOGITS
     item
    3.55
     Item
    3.10
    item
    3.07
    Item
    3.00
     ITEM
    2.63
     items
    2.43
    ITEM
    2.35
     Items
    2.16
    Items
    1.94
     ITEMS
    1.92
    Activations Density 0.120%

    No Known Activations