© 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. 3112
    Prev
    Next
    INDEX
    Explanations

    instances of LaTeX package usage in a document

    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
     EdgeInsets
    -0.77
    TabIndex
    -0.72
    gdx
    -0.66
    @[+][
    -0.66
    EndContext
    -0.60
    tagHelper
    -0.58
    MouseEvent
    -0.58
    jspx
    -0.58
     SqlDbType
    -0.57
    amssymb
    -0.57
    POSITIVE LOGITS
    endregion
    1.83
    //
    1.07
     endregion
    1.00
    TagHelper
    0.96
    :✨
    0.94
    WriteLiteral
    0.89
    __(/*!
    0.87
    usepackage
    0.87
    </thead>
    0.85
    الإنجليزية
    0.76
    Activations Density 0.023%

    No Known Activations