© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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 - 65k
    9. 16-GEMMASCOPE-RES-65K
    11. 29780
    Prev
    Next
    INDEX
    Explanations

    descriptors of written material and their effectiveness

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

    positive evaluations of quality or function

    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
    Not in Any Lists

    No Comments

    Negative Logits
    хьтан
    -0.84
    BorderFactory
    -0.66
     siglas
    -0.60
     Italijanski
    -0.59
     Dependence
    -0.59
     AppModule
    -0.57
     referenties
    -0.57
     Bancroft
    -0.56
     Mercantile
    -0.56
     deadliest
    -0.56
    POSITIVE LOGITS
     adequately
    0.79
     nicely
    0.78
     timely
    0.77
     reasonably
    0.74
     accurate
    0.71
     adequate
    0.71
     reasonable
    0.71
     accurately
    0.70
     sufficiently
    0.69
    もしっかり
    0.68
    Activations Density 0.143%

    No Known Activations