© 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 - 131k
    9. 20-GEMMASCOPE-RES-131K
    11. 104197
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    parsedMessage
    -0.99
     zwiſchen
    -0.97
     Dieſe
    -0.96
    <unused43>
    -0.96
    <pad>
    -0.96
    <unused79>
    -0.95
     ſeiner
    -0.95
    <unused41>
    -0.95
    <unused3>
    -0.95
    <unused16>
    -0.95
    POSITIVE LOGITS
    elementAt
    2.42
    ContainerState
    1.51
    InitStruct
    0.64
     objectAtIndex
    0.60
    blurRadius
    0.58
    ItemLayout
    0.52
    InitStructure
    0.51
    hasMoreElements
    0.51
    ElementAt
    0.50
    compareTo
    0.46
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.