© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 21-GEMMASCOPE-RES-16K
    11. 11940
    Prev
    Next
    INDEX
    Explanations

    titles and names in structured data

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    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
     sulit
    -0.27
     przecież
    -0.26
     vernie
    -0.24
     value
    -0.23
     priests
    -0.23
    apiVersion
    -0.23
     experimental
    -0.23
     kual
    -0.23
     available
    -0.22
     siihen
    -0.22
    POSITIVE LOGITS
    
    0.93
     AssemblyTitle
    0.87
    AutoScaleMode
    0.86
     ModelExpression
    0.79
    Personendaten
    0.73
    Искәрмәләр
    0.73
     titel
    0.69
     ujednoznacz
    0.69
     AssemblyProduct
    0.68
     propOrder
    0.68
    Activations Density 0.346%

    No Known Activations