© 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. 13-GEMMASCOPE-RES-65K
    6. 5195
    Prev
    Next
    INDEX
    Explanations

    sequences of numbers and letters often associated with data or codes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 13-gemmascope-res-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_13/width_65k/average_l0_75
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    Data Type
    float32
    Hook Name
    blocks.13.hook_resid_post
    Hook Layer
    13
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ModelExpression
    -0.79
    kuuta
    -0.71
    ContentAlignment
    -0.67
    hyrchwyd
    -0.66
     Bourgoin
    -0.64
    orsese
    -0.57
    azgo
    -0.57
    IntoConstraints
    -0.56
    ẾT
    -0.56
    LabelTagHelper
    -0.55
    POSITIVE LOGITS
    üten
    0.52
    WillAppear
    0.46
    SpringBootTest
    0.45
    出版年
    0.45
    tagext
    0.45
    ServletException
    0.45
    glBindBuffer
    0.45
    DoubleQuotes
    0.45
    رشف
    0.45
    ExtendWith
    0.43
    Activations Density 0.029%

    No Known Activations