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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 4346
    Prev
    Next
    INDEX
    Explanations

    mathematical statements and notations related to statistics and probability theory

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

    Mathematical or equation context

    np_acts-logits-general · gemini-2.0-flash

    introduction to equations

    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
    NUMX
    -0.86
    出版年
    -0.77
    !")
    -0.72
     ddelweddau
    -0.70
    Clik
    -0.68
    脚注の使い方
    -0.67
    
    -0.66
    "</
    -0.66
    KommentareTeilen
    -0.66
     jspb
    -0.65
    POSITIVE LOGITS
    :
    1.02
    ↵↵
    0.98
    \[
    0.74
    ↵↵↵
    0.70
     suivante
    0.67
     $$
    0.64
     :
    0.61
    :$
    0.58
    ：
    0.58
    ↵↵↵↵
    0.56
    Activations Density 1.793%

    No Known Activations