© 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. 24-GEMMASCOPE-RES-16K
    11. 14673
    Prev
    Next
    INDEX
    Explanations

    terms related to statistical methods and medical study designs

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

    Abbreviations and symbols within scientific texts

    np_acts-logits-general · gemini-2.0-flash

    Abbreviations and scientific terms

    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
    ритори
    -0.53
    NewReader
    -0.49
    mybatisplus
    -0.48
     חיצוניים
    -0.47
     lccn
    -0.46
     Италијани
    -0.45
     <=",
    -0.44
    Хьажоргаш
    -0.44
    テンツ
    -0.43
    odha
    -0.43
    POSITIVE LOGITS
     himſelf
    0.69
     ſtate
    0.65
     ſhall
    0.63
     Efq
    0.63
     Majefty
    0.62
     ſever
    0.62
     seaborn
    0.62
     fubject
    0.61
     science
    0.60
     ftate
    0.59
    Activations Density 0.833%

    No Known Activations