© 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. 4-GEMMASCOPE-RES-16K
    11. 16066
    Prev
    Next
    INDEX
    Explanations

    JavaScript and DOM manipulation functions and methods

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.hook_resid_post
    Hook Layer
    4
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     themſelves
    -0.69
     barbati
    -0.68
    RenderAtEndOf
    -0.67
     quæ
    -0.67
     niedersachsen
    -0.66
     Monfieur
    -0.63
     köln
    -0.63
     rechange
    -0.62
     pleaſure
    -0.62
     Turquie
    -0.61
    POSITIVE LOGITS
    addEventListener
    1.68
    dom
    0.95
    classList
    0.95
     dom
    0.82
    EventListener
    0.81
    DOM
    0.76
    querySelector
    0.75
    printStackTrace
    0.73
     DOM
    0.70
    
    0.70
    Activations Density 0.028%

    No Known Activations