© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 2-GEMMASCOPE-RES-16K
    11. 8364
    Prev
    Next
    INDEX
    Explanations

    terms related to importing and exportation of goods

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    sizeCache
    -0.78
    secta
    -0.71
     GetEnumerator
    -0.70
    ForValue
    -0.70
    ьаж
    -0.69
    Климат
    -0.68
    Tikang
    -0.67
     дописавши
    -0.67
    Referanser
    -0.65
    ImageContext
    -0.64
    POSITIVE LOGITS
     imports
    2.99
     import
    2.97
     Import
    2.85
     imported
    2.74
     Imports
    2.58
    Import
    2.55
     importing
    2.50
     Imported
    2.38
     importation
    2.34
    Imports
    2.32
    Activations Density 0.072%

    No Known Activations