© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 65k
    5. 20-GEMMASCOPE-RES-65K
    6. 1805
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_65k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    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
    TagMode
    -0.81
     kaffe
    -0.70
    SequentialGroup
    -0.68
    SourceChecksum
    -0.68
    letoe
    -0.67
    RegistryLite
    -0.67
     Kaffee
    -0.64
     مرئيه
    -0.62
    principalTable
    -0.60
    UpInside
    -0.60
    POSITIVE LOGITS
     tasted
    0.90
     recipe
    0.90
     flavour
    0.89
     flavorful
    0.88
     cooked
    0.88
     taste
    0.88
     tastes
    0.86
     flavor
    0.85
     flavours
    0.83
     ingredients
    0.82
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.