© 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. 12430
    Prev
    Next
    INDEX
    Explanations

    references to mathematical or computational analyses involving large quantities or simulations

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

    the letter "N"

    np_acts-logits-general · gemini-2.0-flash

    large N

    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
    RegressionTest
    -0.63
     BoxDecoration
    -0.61
    مصادر
    -0.55
     ویکی‌آمباردا
    -0.49
    ագրություններ
    -0.49
    cmu
    -0.48
    newswire
    -0.47
    Démographie
    -0.45
    LabelTagHelper
    -0.45
    enio
    -0.45
    POSITIVE LOGITS
     N
    3.61
    N
    3.12
    Ｎ
    1.93
     n
    1.92
    getN
    1.92
    setN
    1.91
     Н
    1.67
    n
    1.47
     ن
    1.43
    Ns
    1.37
    Activations Density 0.844%

    No Known Activations