© 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. 16-GEMMASCOPE-RES-16K
    11. 2154
    Prev
    Next
    INDEX
    Explanations

    technical terms and concepts related to physics equations and mechanics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Sentences defining or describing a "term"

    np_acts-logits-general · gemini-2.0-flash

    terms describe components

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     isother
    -0.51
    Leng
    -0.50
    َع
    -0.49
    Interv
    -0.48
     BIN
    -0.48
    jores
    -0.48
     Luch
    -0.48
    circledR
    -0.48
     Suprema
    -0.46
     NSCoder
    -0.46
    POSITIVE LOGITS
     contribution
    0.82
    RenderAtEndOf
    0.77
     contributo
    0.76
     contributions
    0.75
    SerializedSize
    0.72
     contribución
    0.72
    Contribution
    0.72
    contribution
    0.70
     component
    0.68
     addition
    0.66
    Activations Density 1.733%

    No Known Activations