© 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-2-9B
    4. Residual Stream - 16k
    5. 21-GEMMASCOPE-RES-16K
    6. 2961
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_21/width_16k/average_l0_129
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    httphttps
    -0.77
    GraphicsUnit
    -0.72
     totalCount
    -0.71
     AssemblyCompany
    -0.70
     BoxDecoration
    -0.70
    InjectAttribute
    -0.69
     ſind
    -0.68
     faſt
    -0.67
    MLLoader
    -0.67
    SequentialGroup
    -0.67
    POSITIVE LOGITS
    _
    1.33
    \_
    0.91
    -
    0.79
    ‐
    0.75
    -​
    0.69
    _{
    0.68
    ‑
    0.65
    }_
    0.64
     _
    0.64
    ・
    0.61
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.