© 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-IT
    7. Residual Stream - 131k
    9. 9-GEMMASCOPE-RES-131K
    11. 125369
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_131k/average_l0_121
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     demek
    -0.37
    icoot
    -0.33
    serviceWorker
    -0.28
     minOccurs
    -0.28
    roveň
    -0.27
     dėl
    -0.25
     trực
    -0.25
     ła
    -0.24
     vì
    -0.23
     disant
    -0.23
    POSITIVE LOGITS
    Personendaten
    0.92
    UnusedPrivate
    0.87
    SourceChecksum
    0.85
     betweenstory
    0.84
    msgTypes
    0.83
    rawDesc
    0.82
    TagMode
    0.80
    Diwedd
    0.78
    MLLoader
    0.74
     Taktlose
    0.74
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.