© 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. 4730
    Prev
    Next
    INDEX
    Explanations

    elements related to web development frameworks and stylesheets

    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
     ferons
    -0.55
     sauvages
    -0.52
     fråga
    -0.51
     sätt
    -0.50
    berdayakan
    -0.48
    \{\\
    -0.47
     dirait
    -0.47
     arşivlendi
    -0.46
     récomp
    -0.46
    DebuggerNonUser
    -0.46
    POSITIVE LOGITS
    
    1.02
    stylesheet
    0.78
     [*]
    0.67
     RT
    0.61
     Initialized
    0.61
    Personendaten
    0.60
    HtmlAttribute
    0.57
     Himo
    0.57
     AppCompatTheme
    0.56
     gainera
    0.56
    Activations Density 1.894%

    No Known Activations