© 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. 624
    Prev
    Next
    INDEX
    Explanations

    numerical data or structured data formats, such as percentages or codes

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

    structured data formats or identifiers likely related to programming or databases

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

    to after comma

    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
    webElementXpaths
    -0.89
     betweenstory
    -0.89
    :✨
    -0.88
     resourceCulture
    -0.88
     Савезне
    -0.80
    verwijspagina
    -0.79
    NameInMap
    -0.77
    ьаж
    -0.73
    InstanceState
    -0.70
    webElement
    -0.69
    POSITIVE LOGITS
     to
    1.63
    to
    1.26
     To
    1.19
    To
    1.15
     TO
    0.97
    到
    0.86
    setTo
    0.83
    nto
    0.69
    tothe
    0.66
     unto
    0.65
    Activations Density 0.128%

    No Known Activations