© 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-2-2B
    7. Residual Stream - 16k
    9. 24-GEMMASCOPE-RES-16K
    11. 9173
    Prev
    Next
    INDEX
    Explanations

    terms related to items or items' attributes in a dataset

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

    "item" or "Item"

    np_acts-logits-general · gemini-2.0-flash

    itemized or itemization

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    TagMode
    -0.61
    IntoConstraints
    -0.57
    Diweddarwch
    -0.55
    ConstraintMaker
    -0.53
    GraphicsUnit
    -0.51
    Gambas
    -0.51
    ScopeManager
    -0.51
     Мексичка
    -0.51
     otomatig
    -0.49
     GenerationType
    -0.49
    POSITIVE LOGITS
    ized
    1.12
    ization
    0.91
    ised
    0.91
    izing
    0.88
    IZED
    0.78
    ize
    0.75
     getItem
    0.74
    izes
    0.73
    izers
    0.73
    izations
    0.67
    Activations Density 0.042%

    No Known Activations