© 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-2-2B
    7. Residual Stream - 65k
    9. 0-GEMMASCOPE-RES-65K
    11. 10195
    Prev
    Next
    INDEX
    Explanations

    words expressing improvement or enhancement

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 0-gemmascope-res-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_0/width_65k/average_l0_73
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    Data Type
    float32
    Hook Name
    blocks.0.hook_resid_post
    Hook Layer
    0
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     jLabel
    -0.87
     jScrollPane
    -0.72
    Revenir
    -0.68
    存于互联网档案馆
    -0.63
    SequentialGroup
    -0.60
    
    -0.59
     שוליים
    -0.59
     Pula
    -0.59
     presse
    -0.59
     Theſe
    -0.59
    POSITIVE LOGITS
     better
    2.16
    better
    2.05
    Better
    2.02
     Better
    1.98
     BETTER
    1.73
     mejor
    1.59
     melhor
    1.48
     besser
    1.45
     improved
    1.39
    mejor
    1.37
    Activations Density 0.061%

    No Known Activations