© 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 - 16k
    9. 21-GEMMASCOPE-RES-16K
    11. 9837
    Prev
    Next
    INDEX
    Explanations

    references to specific government actions or diplomatic events

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 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
    Negative Logits
     prioritizing
    -0.84
     transitioning
    -0.84
     showcased
    -0.83
     showcasing
    -0.83
     prioritize
    -0.80
     transitioned
    -0.79
     prioritized
    -0.77
     showcase
    -0.74
     showcases
    -0.74
     referenced
    -0.74
    POSITIVE LOGITS
     skall
    0.84
    MLLoader
    0.79
     thereupon
    0.75
     daß
    0.64
    ReusableCell
    0.62
    faßt
    0.61
     giebt
    0.61
     forthwith
    0.61
     thence
    0.59
    %</
    0.56
    Activations Density 0.712%

    No Known Activations