© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 10824
    Prev
    Next
    INDEX
    Explanations

    phrases related to the concept of "no one" or universal negation

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

    "Never" or "nobody" contexts

    np_acts-logits-general · gemini-2.0-flash

    no one says

    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
    rrggbb
    -0.53
     Roskov
    -0.52
    each
    -0.52
    )]);
    -0.51
     only
    -0.46
    óż
    -0.44
    eens
    -0.44
     Améli
    -0.44
     censiti
    -0.44
    Населення
    -0.44
    POSITIVE LOGITS
     ever
    1.05
     EVER
    0.91
     jemals
    0.87
     تانيه
    0.77
     Ever
    0.75
    Ever
    0.72
     excepto
    0.71
     jamais
    0.70
     except
    0.70
     ninguém
    0.69
    Activations Density 0.181%

    No Known Activations