© 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. 0-GEMMASCOPE-RES-65K
    6. 10141
    Prev
    Next
    INDEX
    Explanations

    references to "structure" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered 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
    Not in Any Lists

    No Comments

    Negative Logits
     crdi
    -0.77
     Jérusalem
    -0.74
    esModule
    -0.67
     faſt
    -0.67
     муніципалі
    -0.66
     boreal
    -0.65
     Knives
    -0.64
     fotografico
    -0.64
     Theſe
    -0.63
     NDEBUG
    -0.63
    POSITIVE LOGITS
     structure
    3.67
     Structure
    3.48
    structure
    3.38
    Structure
    3.36
     structures
    3.28
     Structures
    3.08
     STRUCTURE
    3.06
    struct
    3.03
     struct
    3.00
     Struct
    2.97
    Activations Density 0.057%

    No Known Activations