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

    Neuronpedia

    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. 16884
    Prev
    Next
    INDEX
    Explanations

    instances of conjunctions, particularly "and" and "but," that connect phrases and ideas

    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
    "]];
    -0.76
     therefor
    -0.71
     utilise
    -0.65
     ControllerBase
    -0.62
     CreateTagHelper
    -0.62
     utilising
    -0.61
     diatas
    -0.61
    */}
    -0.60
     similaire
    -0.60
    "]));
    -0.59
    POSITIVE LOGITS
     дописавши
    0.68
    awtextra
    0.61
    ollectionView
    0.59
    GetAxis
    0.59
    ">//
    0.58
     rast
    0.55
     nahilalakip
    0.55
     eminently
    0.54
    INCE
    0.54
    ÉL
    0.53
    Activations Density 0.063%

    No Known Activations