© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 30-GEMMASCOPE-RES-16K
    11. 10720
    Prev
    Next
    INDEX
    Explanations

    references to items or elements within a structured context

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

    the word "item" (often capitalized)

    np_acts-logits-general · gemini-2.0-flash

    item or items

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 30-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_30/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.30.hook_resid_post
    Hook Layer
    30
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     arşivlendi
    -0.59
    raulic
    -0.54
    OGND
    -0.47
    hasErrors
    -0.46
     prêtres
    -0.45
    存于互联网档案馆
    -0.44
     محفوظة
    -0.44
    parsedMessage
    -0.44
     Económica
    -0.44
     leaſt
    -0.44
    POSITIVE LOGITS
     Item
    0.71
     addItem
    0.64
     item
    0.64
     getItem
    0.63
    GetItem
    0.61
    getItem
    0.60
    itemType
    0.59
    ization
    0.58
     Items
    0.57
     ITEM
    0.57
    Activations Density 0.084%

    No Known Activations