© 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. 11-GEMMASCOPE-RES-16K
    6. 4333
    Prev
    Next
    INDEX
    Explanations

    historical or mythical figures and their roles in events

    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
    RegressionTest
    -0.67
    LookAnd
    -0.62
    TagMode
    -0.62
    رشف
    -0.54
     mergeFrom
    -0.51
     "..\..\..\
    -0.49
    CloseOperation
    -0.48
     "..\..\
    -0.48
    Искәрмәләр
    -0.46
    XmlType
    -0.46
    POSITIVE LOGITS
    endenza
    0.59
     rallado
    0.57
    Hardness
    0.55
    KELEY
    0.54
     picado
    0.53
    interopRequire
    0.53
     aio
    0.52
    eramente
    0.51
    amus
    0.50
    тері
    0.49
    Activations Density 0.613%

    No Known Activations