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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 28-GEMMASCOPE-RES-16K
    11. 4600
    Prev
    Next
    INDEX
    Explanations

    elements or attributes related to items in a structured data context, such as lists or arrays

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

    the word "item" (capitalized or not)

    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 @ 28-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_28/width_16k/average_l0_119
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.28.hook_resid_post
    Hook Layer
    28
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     TextInputType
    -0.55
    XmlAccessType
    -0.51
     Brakes
    -0.47
     arşivlendi
    -0.45
     McLaughlin
    -0.44
     Sudbury
    -0.44
    nsics
    -0.44
    ughty
    -0.44
    hasErrors
    -0.43
     calabaza
    -0.43
    POSITIVE LOGITS
     Item
    1.02
     item
    0.88
    Item
    0.85
     ITEM
    0.85
     getItem
    0.80
     Items
    0.79
    getItem
    0.78
    itemType
    0.77
     items
    0.73
     itemId
    0.72
    Activations Density 0.096%

    No Known Activations