© 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. 11-GEMMASCOPE-RES-16K
    11. 5063
    Prev
    Next
    INDEX
    Explanations

    dates and timelines associated with events or processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Hook Layer
    11
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    matchCondition
    -0.70
     Transient
    -0.52
    Olvid
    -0.51
    rocław
    -0.47
    اظ
    -0.47
    Transient
    -0.46
    ForRow
    -0.46
    tellt
    -0.46
     advertisers
    -0.46
    olate
    -0.45
    POSITIVE LOGITS
    WithIOException
    0.61
    URLException
    0.60
    FormTagHelper
    0.59
     ModelExpression
    0.57
    AccessorTable
    0.57
    PickerController
    0.57
     hurry
    0.56
     propOrder
    0.54
     AssemblyCompany
    0.54
     архивлан
    0.53
    Activations Density 0.408%

    No Known Activations