© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 65k
    9. 13-GEMMASCOPE-RES-65K
    11. 8277
    Prev
    Next
    INDEX
    Explanations

    phrases emphasizing optimization and maximum efficiency in various contexts

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 13-gemmascope-res-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_13/width_65k/average_l0_75
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    Data Type
    float32
    Hook Name
    blocks.13.hook_resid_post
    Hook Layer
    13
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
    spyOn
    -0.48
    Erreferentziak
    -0.47
     popolo
    -0.46
    wood
    -0.45
    児
    -0.45
    ıştı
    -0.44
    buttonShape
    -0.44
     ostavi
    -0.43
     semp
    -0.43
    édi
    -0.42
    POSITIVE LOGITS
     maximize
    1.22
     maximizing
    1.16
     maximized
    1.09
     maximizes
    1.05
     maximise
    1.01
     Maximize
    0.99
     optimum
    0.98
    maximize
    0.97
     optimize
    0.96
     maximum
    0.94
    Activations Density 0.057%

    No Known Activations