© 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 - 65k
    9. 20-GEMMASCOPE-RES-65K
    11. 2749
    Prev
    Next
    INDEX
    Explanations

    HTML and JavaScript structural elements related to user interface components

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    html tags and attributes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_65k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    emiah
    -0.52
    polic
    -0.50
    theim
    -0.48
    iterrane
    -0.48
     Ter
    -0.47
    bro
    -0.45
    opher
    -0.45
    ded
    -0.45
     fizer
    -0.43
    Scalars
    -0.43
    POSITIVE LOGITS
    ReusableCell
    0.89
    ंदीखरीदारी
    0.82
     дописавши
    0.81
     snippetHide
    0.81
     id
    0.79
     betweenstory
    0.76
     Réponses
    0.75
    原始内容存档于
    0.74
    ScopeManager
    0.74
     JpaRepository
    0.72
    Activations Density 0.063%

    No Known Activations