© 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. 31564
    Prev
    Next
    INDEX
    Explanations

    technical or programming-related terms and references to software liability

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    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
    Not in Any Lists

    No Comments

    Negative Logits
    덱
    -0.63
     among
    -0.63
    Hiding
    -0.58
    RegressionTest
    -0.57
    among
    -0.55
    akter
    -0.55
    khó
    -0.54
     Dostupné
    -0.54
    ünst
    -0.54
    tahui
    -0.54
    POSITIVE LOGITS
    FunctionFlags
    0.65
     '\\;'
    0.64
    expandindo
    0.57
     незавершена
    0.56
    vierno
    0.56
    )|^{
    0.53
     Sauber
    0.51
    MarshalTo
    0.50
     diſt
    0.49
    blender
    0.49
    Activations Density 0.002%

    No Known Activations