© 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. 9623
    Prev
    Next
    INDEX
    Explanations

    C++ standard library components and functions

    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
     تضيفلها
    -0.92
    queryInterface
    -0.83
     يتيمه
    -0.81
     становника
    -0.78
    IntoConstraints
    -0.76
     kasarigan
    -0.76
     Signalez
    -0.75
     Exactos
    -0.74
    клопе
    -0.74
    AsUp
    -0.73
    POSITIVE LOGITS
     std
    0.68
    std
    0.58
     emoc
    0.53
     deviation
    0.52
    Deviation
    0.50
    Std
    0.49
    DEV
    0.48
    iostream
    0.48
    stringValue
    0.47
     dev
    0.47
    Activations Density 0.040%

    No Known Activations