© 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. 18-GEMMASCOPE-RES-16K
    11. 1323
    Prev
    Next
    INDEX
    Explanations

    phrases and sentences related to quantification or measurement

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

    "of [something plural]"

    np_acts-logits-general · gemini-2.0-flash

    group of seven

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     rêves
    -0.65
     chré
    -0.64
     leçons
    -0.61
     dieux
    -0.59
     larmes
    -0.59
     navires
    -0.58
     pères
    -0.57
     témoins
    -0.57
     attentes
    -0.56
     dilan
    -0.56
    POSITIVE LOGITS
     sorts
    0.85
    Personensuche
    0.84
    NameInMap
    0.82
    `,
    0.80
     interrelated
    0.79
     interconnected
    0.77
     six
    0.75
    '>";
    0.75
     seven
    0.74
    )";
    0.73
    Activations Density 0.303%

    No Known Activations