© 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. 5701
    Prev
    Next
    INDEX
    Explanations

    terminology related to radiation and radio technology

    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
     Italijanski
    -0.97
    uxxxx
    -0.88
    onAttach
    -0.86
    bootstrapcdn
    -0.83
    RenderAtEndOf
    -0.81
    (',')
    -0.80
     propOrder
    -0.78
     Messina
    -0.75
     Hirst
    -0.75
     Husbandry
    -0.74
    POSITIVE LOGITS
     Rad
    2.36
    Rad
    2.27
     rad
    2.18
    rad
    2.02
     RAD
    1.92
    RAD
    1.79
     Radi
    1.43
     radiation
    1.35
     radi
    1.35
    Radi
    1.33
    Activations Density 0.247%

    No Known Activations