© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 3-GEMMASCOPE-RES-16K
    11. 2494
    Prev
    Next
    INDEX
    Explanations

    the repeated use of the word "and" in varying contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     matter
    -0.52
     riuscito
    -0.47
    aw
    -0.44
    ါ
    -0.44
     mulighed
    -0.43
    instance
    -0.43
    \{
    -0.42
    NamedQueries
    -0.41
     раза
    -0.41
     sää
    -0.41
    POSITIVE LOGITS
    IUrlHelper
    0.75
    PerformLayout
    0.74
    Архівовано
    0.74
    Населення
    0.73
    最快更新
    0.73
    SerializedSize
    0.72
    glBegin
    0.72
    MarshalTo
    0.70
     समीक्षाओं
    0.68
     JpaRepository
    0.67
    Activations Density 0.104%

    No Known Activations