© 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. 20-GEMMASCOPE-RES-16K
    11. 1297
    Prev
    Next
    INDEX
    Explanations

    statements or quotes attributed to individuals, particularly in contexts involving announcements or reports

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

    Follows a quote

    np_acts-logits-general · gemini-2.0-flash

    reported speech attribution

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     venner
    -0.52
    abetes
    -0.48
    emm
    -0.48
     meille
    -0.48
    kuere
    -0.47
    rgba
    -0.47
    FormItem
    -0.47
     '{@
    -0.47
    hynch
    -0.46
     impresa
    -0.46
    POSITIVE LOGITS
    Obrázky
    0.81
     ***!
    0.77
     further
    0.69
    abestanden
    0.69
     تانيه
    0.67
     Further
    0.65
    ⓧ
    0.65
     noting
    0.64
    urther
    0.63
     kasarigan
    0.63
    Activations Density 0.062%

    No Known Activations