© 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. 2622
    Prev
    Next
    INDEX
    Explanations

    words and phrases indicating birth, death, and significant events in a person's life timeline

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

    births, launches, or publications

    np_acts-logits-general · gemini-2.0-flash

    birth and origins

    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
     areas
    -0.42
    ↵↵
    -0.42
    <eos>
    -0.41
     A
    -0.40
     par
    -0.38
     de
    -0.38
     spatial
    -0.37
    licable
    -0.37
     files
    -0.36
    -
    -0.36
    POSITIVE LOGITS
     Theſe
    0.94
    TagMode
    0.93
     kasarigan
    0.90
    SequentialGroup
    0.89
    ftagPool
    0.88
    BeginContext
    0.88
     Efq
    0.87
     uſed
    0.84
     referenties
    0.84
     MainAxisSize
    0.83
    Activations Density 0.473%

    No Known Activations