© 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. 5-GEMMASCOPE-RES-16K
    11. 15341
    Prev
    Next
    INDEX
    Explanations

    occurrences of HTML and JavaScript component structure indicators

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    springframework
    -0.57
    djangoproject
    -0.55
    ($('#
    -0.54
    ണ
    -0.53
    жав
    -0.52
    cshtml
    -0.51
     getView
    -0.51
     Saddam
    -0.50
     Koenig
    -0.50
    dpi
    -0.49
    POSITIVE LOGITS
    lg
    1.71
     lg
    1.31
     CreateTagHelper
    1.09
    LG
    1.06
    addContainerGap
    1.01
    Lg
    0.97
     LG
    0.97
    ValueStyle
    0.96
    AnchorStyles
    0.94
    GeoNames
    0.82
    Activations Density 0.011%

    No Known Activations