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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 24-GEMMASCOPE-RES-16K
    11. 4255
    Prev
    Next
    INDEX
    Explanations

    references to the term "Ny" and its related variations or contexts

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

    Words/tokens often followed by country names

    np_acts-logits-general · gemini-2.0-flash

    Ny followed by names or code

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    tvguidetime
    -0.55
    ISupport
    -0.55
     الحره
    -0.55
     Geraadpleegd
    -0.52
     resourceCulture
    -0.49
     Winfrey
    -0.49
    pya
    -0.49
    SequentialGroup
    -0.48
     Byzantium
    -0.48
     SwitchCompat
    -0.47
    POSITIVE LOGITS
    '],
    0.52
     Zan
    0.51
    Zan
    0.50
     ");
    0.50
     "));
    0.50
    %");
    0.49
    Tembelea
    0.48
     Tan
    0.48
     tahan
    0.47
     européens
    0.47
    Activations Density 0.027%

    No Known Activations