© 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. 20-GEMMASCOPE-RES-131K
    11. 100308
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    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
    setVerticalGroup
    -0.94
    parsedMessage
    -0.89
    expandindo
    -0.87
    piram
    -0.82
     AssemblyCulture
    -0.82
    IsMutable
    -0.82
    WithIOException
    -0.80
     Taktlose
    -0.76
    IUrlHelper
    -0.76
    awtextra
    -0.74
    POSITIVE LOGITS
     rayas
    0.33
     during
    0.31
     palsu
    0.30
     botines
    0.30
     remarks
    0.29
     formales
    0.29
     muchacha
    0.28
     Schreib
    0.27
    loroethene
    0.27
     estren
    0.26
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.