© 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. 4530
    Prev
    Next
    INDEX
    Explanations

    phrases indicating time or temporal references

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

    "As of" followed by a time period

    np_acts-logits-general · gemini-2.0-flash

    as of

    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
     spricht
    -0.46
    cuma
    -0.45
    glEnd
    -0.44
    perties
    -0.43
    тере
    -0.43
    yson
    -0.43
    <eos>
    -0.42
    abstra
    -0.41
     برانيه
    -0.41
    Скачать
    -0.41
    POSITIVE LOGITS
     initComponents
    0.84
    esgue
    0.71
    Tikang
    0.70
    FTFY
    0.70
    прочем
    0.69
     AssemblyProduct
    0.67
     Efq
    0.67
     Paglinawan
    0.67
    Aiheesta
    0.67
    ledem
    0.67
    Activations Density 0.226%

    No Known Activations