© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 325
    Prev
    Next
    INDEX
    Explanations

    references to development tools and configurations in programming contexts

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

    technical terms related to software project dependencies and build systems

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

    build configuration code

    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
     muualla
    -0.75
    fjspx
    -0.71
     препратки
    -0.70
    contentLoaded
    -0.68
     فريبيس
    -0.66
    ThroughAttribute
    -0.65
     linking
    -0.64
     link
    -0.64
     للمعارف
    -0.64
    脚注の使い方
    -0.63
    POSITIVE LOGITS
     J
    0.45
    йс
    0.41
    '])->
    0.40
    vine
    0.39
    روم
    0.39
     Jak
    0.39
     hot
    0.38
     Hot
    0.38
    ']))
    0.38
    <bos>
    0.37
    Activations Density 0.233%

    No Known Activations