Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 5-GEMMASCOPE-RES-16K
    6. 2694
    Prev
    Next
    INDEX
    Explanations

    code-related terms, particularly those related to querying and manipulating elements in the Document Object Model (DOM)

    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
     Cluj
    -0.73
    protoimpl
    -0.72
     bath
    -0.66
    Eloquent
    -0.64
     stream
    -0.64
    Rath
    -0.62
     setId
    -0.61
    ;#
    -0.60
    FACT
    -0.60
     estimés
    -0.59
    POSITIVE LOGITS
    querySelector
    3.17
    querySelectorAll
    1.70
    Selector
    0.66
     defStyleAttr
    0.65
    keteers
    0.62
     otr
    0.62
     Pellegrini
    0.61
    PageModule
    0.61
    setOnAction
    0.60
    parseColor
    0.59
    Activations Density 0.030%

    No Known Activations