© 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. 10-GEMMASCOPE-RES-16K
    11. 5972
    Prev
    Next
    INDEX
    Explanations

    phrases related to events and actions occurring in a narrative context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_10/width_16k/average_l0_113
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ValueStyle
    -0.59
     незавершена
    -0.54
    ⇑
    -0.51
     autorytatywna
    -0.48
    :✨
    -0.48
    NameInMap
    -0.45
     ExecuteAsync
    -0.44
    InitVars
    -0.42
    DropColumn
    -0.42
    ScopeManager
    -0.41
    POSITIVE LOGITS
    alakip
    0.57
     montanha
    0.54
     duquel
    0.54
    Linki
    0.50
     conciencia
    0.48
     prévue
    0.48
     táctil
    0.48
     consciência
    0.47
     sää
    0.47
    stdafx
    0.47
    Activations Density 8.085%

    No Known Activations