© 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. 3-GEMMASCOPE-RES-16K
    11. 2596
    Prev
    Next
    INDEX
    Explanations

    LaTeX package commands, particularly those related to document formatting and mathematical symbols

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    iostream
    -0.76
     дописавши
    -0.70
     quæ
    -0.64
     vů
    -0.62
     domésticos
    -0.62
    wsgi
    -0.62
     endforeach
    -0.60
     django
    -0.57
     urbanos
    -0.55
     úteis
    -0.55
    POSITIVE LOGITS
    IMPORTED
    1.09
    bootstrapcdn
    1.06
    GroupLayout
    1.01
    usepackage
    0.99
     TextStyle
    0.94
     stub
    0.93
    tagHelper
    0.91
    cshtml
    0.90
    webElementGuid
    0.88
     BorderSide
    0.82
    Activations Density 0.005%

    No Known Activations