© 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. 58053
    Prev
    Next
    INDEX
    Explanations

    terms related to statistical modeling and estimators in time series analysis

    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
    #+#
    -0.70
    PROTOBUF
    -0.61
     NSCoder
    -0.57
     kamp
    -0.53
    ndale
    -0.53
    standers
    -0.53
     Preferencias
    -0.52
    Kamp
    -0.52
     Rodin
    -0.51
     AssemblyProduct
    -0.51
    POSITIVE LOGITS
     forecasting
    0.61
    styleType
    0.57
     forecast
    0.56
     kasarigan
    0.56
     murale
    0.56
     chronique
    0.55
     HasFactory
    0.55
     macroeconomic
    0.54
     économ
    0.52
     Forecasting
    0.51
    Activations Density 0.146%

    No Known Activations