© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 65k
    5. 20-GEMMASCOPE-RES-65K
    6. 1598
    Prev
    Next
    INDEX
    Explanations

    technical or coded language related to computational elements

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

    elements of code or syntax in a programming context

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

    statistics and financial terms

    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
    existsSync
    -0.47
    UrlResolution
    -0.44
     Erişim
    -0.42
     disconnecting
    -0.40
    kusi
    -0.39
    FieldDescriptor
    -0.38
     O
    -0.36
    SqlServer
    -0.36
     oto
    -0.36
    羽毛
    -0.35
    POSITIVE LOGITS
    ViewFeatures
    1.20
    \{\\
    0.77
     nakalista
    0.73
    /**
    0.73
     '\\;'
    0.72
    RectangleBorder
    0.72
    plevel
    0.71
    ConverterFactory
    0.71
     GoogleFonts
    0.70
    AndEndTag
    0.69
    Activations Density 0.064%

    No Known Activations