© 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. 2543
    Prev
    Next
    INDEX
    Explanations

    words related to mathematical concepts and constructions

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

    ending in "-ation," "-tion," or "-ally."

    np_acts-logits-general · gemini-2.0-flash

    suffixes like ation, ally, tion

    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
    التالي
    -0.84
    AnchorStyles
    -0.84
    urnum
    -0.74
    ibatis
    -0.73
    hirts
    -0.71
    NewGuid
    -0.71
    ်
    -0.71
    ernalia
    -0.69
    ELTS
    -0.68
    IBar
    -0.67
    POSITIVE LOGITS
    ally
    1.42
    ization
    1.05
    ation
    1.04
    cination
    1.03
    ration
    0.97
    ality
    0.97
    ists
    0.94
    als
    0.91
    ary
    0.87
    ATION
    0.83
    Activations Density 1.944%

    No Known Activations