© 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. 11-GEMMASCOPE-RES-16K
    11. 9168
    Prev
    Next
    INDEX
    Explanations

    technical terms related to data and its analysis

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 11-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_11/width_16k/average_l0_118
    Prompts (Dashboard)
    24,576 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
    ValueStyle
    -0.70
     незавершена
    -0.68
     autorytatywna
    -0.66
    ScopeManager
    -0.56
    sizeCache
    -0.52
     ExecuteAsync
    -0.52
     חיצוניים
    -0.51
    DropColumn
    -0.51
    NameInMap
    -0.50
    adaptiveStyles
    -0.47
    POSITIVE LOGITS
    Linki
    0.56
    alakip
    0.49
     táctil
    0.48
    Przypisy
    0.47
     ilusión
    0.46
     paraître
    0.45
     montanha
    0.44
     comunión
    0.43
     flexibilidad
    0.43
     resourceCulture
    0.42
    Activations Density 7.557%

    No Known Activations