© 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. 31731
    Prev
    Next
    INDEX
    Explanations

    symbols and mathematical notations related to equations and functions

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

    mathematical notation and code

    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
     estekak
    -0.96
    spesies
    -0.89
    usermodel
    -0.87
     BoxFit
    -0.87
     FetchType
    -0.83
     BorderRadius
    -0.81
     crossorigin
    -0.80
    SuccessListener
    -0.78
    #%%
    -0.77
    AxisAlignment
    -0.75
    POSITIVE LOGITS
    ↵
    0.90
    ↵↵↵
    0.88
    <h3>
    0.87
    <eos>
    0.85
    ↵↵↵↵
    0.84
    [toxicity=0]
    0.83
    ↵↵↵↵↵
    0.83
    <h2>
    0.82
            
    0.81
          
    0.81
    Activations Density 0.001%

    No Known Activations