© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 131k
    9. 20-GEMMASCOPE-RES-131K
    11. 101634
    Prev
    Next
    INDEX
    Explanations

    SQL commands and structures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_131k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    存于互联网档案馆
    -0.72
     TabLayout
    -0.59
    lotl
    -0.57
    afficheront
    -0.55
    agonia
    -0.52
    InjectAttribute
    -0.52
    AnchorTagHelper
    -0.52
    ONAUT
    -0.52
    ayout
    -0.50
     calendriers
    -0.50
    POSITIVE LOGITS
    AlterField
    0.40
    setVerticalGroup
    0.38
    ########.
    0.38
     MessageBoxIcon
    0.36
    keyColumn
    0.35
    currentColor
    0.34
    endregion
    0.34
     autorytatywna
    0.31
    hésite
    0.31
     changé
    0.31
    Activations Density 0.000%

    No Known Activations