© 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-2-9B
    7. Residual Stream - 16k
    9. 21-GEMMASCOPE-RES-16K
    11. 16044
    Prev
    Next
    INDEX
    Explanations

    scientific terms and analytical techniques related to material characterization

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_21/width_16k/average_l0_129
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     '\\;'
    -0.77
    phosa
    -0.62
     nonUne
    -0.61
     NSCoder
    -0.60
     дописавши
    -0.59
     pacchetto
    -0.57
    ंदीखरीदारी
    -0.56
    expandindo
    -0.56
    ChildScrollView
    -0.54
     ویکی‌پدیا
    -0.53
    POSITIVE LOGITS
     investigations
    0.50
     scans
    0.45
     examination
    0.44
     analysis
    0.43
     imaging
    0.43
     spectrometry
    0.43
     examinations
    0.42
     CCTV
    0.41
     scanning
    0.41
    BeginInit
    0.40
    Activations Density 1.485%

    No Known Activations