© 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. 16-GEMMASCOPE-RES-65K
    11. 31898
    Prev
    Next
    INDEX
    Explanations

    code-related terms and concepts in programming and computation

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot

    maximum or upper bound

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_65k/average_l0_128
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
    getMenuInflater
    -0.60
    GOTREF
    -0.59
    ukum
    -0.52
     gång
    -0.52
     Wayback
    -0.52
     landscape
    -0.51
    Kanpo
    -0.50
     getContext
    -0.50
     fain
    -0.50
    Retry
    -0.49
    POSITIVE LOGITS
    Inclusive
    0.60
    yargs
    0.59
    illah
    0.59
    RegistryLite
    0.57
    sizeCache
    0.56
    وحة
    0.56
    Autoritní
    0.54
    inclusive
    0.53
     inclusive
    0.53
    rrggbb
    0.53
    Activations Density 0.215%

    No Known Activations