© 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. 13-GEMMASCOPE-RES-65K
    11. 16539
    Prev
    Next
    INDEX
    Explanations

    instances of differential operators in mathematical expressions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 13-gemmascope-res-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_13/width_65k/average_l0_75
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    Data Type
    float32
    Hook Name
    blocks.13.hook_resid_post
    Hook Layer
    13
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     jsPsych
    -0.98
    ագրություններ
    -0.91
     getIs
    -0.80
     LUMP
    -0.80
    expandindo
    -0.79
    ExecuteReader
    -0.76
     Giver
    -0.72
     LMS
    -0.72
    WebElementEntity
    -0.72
     wireType
    -0.71
    POSITIVE LOGITS
    partial
    1.37
    ∂
    1.34
    Partial
    1.03
     Partial
    1.02
     partial
    1.01
     parti
    0.87
     Parti
    0.84
     parcial
    0.82
    athyroid
    0.80
     PART
    0.77
    Activations Density 0.022%

    No Known Activations