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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 15-GEMMASCOPE-RES-16K
    11. 8896
    Prev
    Next
    INDEX
    Explanations

    HTML-related tags and structure in code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_15/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    CppMethod
    -0.87
     defaultstate
    -0.83
    cassert
    -0.82
     BorderRadius
    -0.79
     noqa
    -0.73
    
    -0.72
     doInBackground
    -0.69
    putExtra
    -0.68
    TestingModule
    -0.68
    TargetException
    -0.67
    POSITIVE LOGITS
     Html
    1.25
    html
    1.21
     HTML
    1.21
    Html
    1.20
     html
    1.19
    HTML
    1.09
    shtml
    0.85
    jsoup
    0.84
    tml
    0.77
    htm
    0.76
    Activations Density 0.102%

    No Known Activations