© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 65k
    9. 0-GEMMASCOPE-RES-65K
    11. 13452
    Prev
    Next
    INDEX
    Explanations

    specific code elements or keywords related to "RE" (likely for "register" or "resource") in various contexts, indicating a focus on registration or recognition in programming or data processing

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 0-gemmascope-res-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_0/width_65k/average_l0_73
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    Data Type
    float32
    Hook Name
    blocks.0.hook_resid_post
    Hook Layer
    0
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
     CreateTagHelper
    -0.89
    WithIOException
    -0.72
    OGND
    -0.72
    BeginContext
    -0.71
    WebServlet
    -0.71
     createState
    -0.69
     nahilalakip
    -0.67
    SharedCtor
    -0.64
    Portale
    -0.63
    simpleType
    -0.60
    POSITIVE LOGITS
    abstractmethod
    0.60
    Awe
    0.59
    ellites
    0.58
    appendTo
    0.57
     SMD
    0.57
     vandens
    0.57
    ressee
    0.57
     Schwert
    0.56
     vanske
    0.55
     agência
    0.55
    Activations Density 0.035%

    No Known Activations