© 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 - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 16281
    Prev
    Next
    INDEX
    Explanations

    mathematical or programming transformations relating to rotation and translation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Homography or coordinate transformation

    np_acts-logits-general · gemini-2.0-flash

    invariance under transformations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Pech
    -0.54
    glBegin
    -0.53
     Social
    -0.48
     Kanz
    -0.48
     Sied
    -0.47
     Marquis
    -0.47
     ExecuteAsync
    -0.47
    +#+#
    -0.47
     Fod
    -0.47
    prov
    -0.47
    POSITIVE LOGITS
     transformations
    1.22
     rotation
    1.17
     transformation
    1.12
     rotations
    1.09
     translation
    1.08
     translations
    1.07
    transform
    1.06
     transform
    1.04
     Transform
    1.03
     Rotation
    1.03
    Activations Density 0.674%

    No Known Activations