© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 22-GEMMASCOPE-RES-16K
    11. 60
    Prev
    Next
    INDEX
    Explanations

    references to important statistical data or metrics

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot

    After "the" and signals of a general statement

    np_acts-logits-general · gemini-2.0-flash

    Given the

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
    最有
    -0.53
    的最
    -0.51
     truest
    -0.51
    WidgetItem
    -0.51
     schönsten
    -0.51
    中最
    -0.50
    adə
    -0.49
    真正的
    -0.48
     nhat
    -0.48
    Worst
    -0.47
    POSITIVE LOGITS
     fact
    1.78
     Tatsache
    1.44
     lack
    1.26
    fact
    1.26
     feit
    1.17
     sheer
    1.09
     fakt
    1.05
     fato
    1.05
     tremendous
    1.04
     dearth
    0.99
    Activations Density 0.614%

    No Known Activations