© 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 - 65k
    9. 20-GEMMASCOPE-RES-65K
    11. 1550
    Prev
    Next
    INDEX
    Explanations

    references to "AR" related to various contexts

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

    references to a specific term or acronym, likely related to a formal designation or category in a legal, organizational, or technical context

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

    AR compounds

    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
    GroupLayout
    -0.53
    kloped
    -0.51
    currentColor
    -0.50
    存于互联网档案馆
    -0.49
    consulté
    -0.48
     genommen
    -0.46
    rova
    -0.46
     sur
    -0.46
     dever
    -0.45
     much
    -0.45
    POSITIVE LOGITS
    AccessorTable
    0.69
    verwijspagina
    0.67
    expandindo
    0.65
    Према
    0.62
    styleUrls
    0.61
    脚注の使い方
    0.57
    parsedMessage
    0.57
    $^{-
    0.56
     فريبيس
    0.56
     @{
    0.55
    Activations Density 0.030%

    No Known Activations