Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 21-GEMMASCOPE-RES-16K
    6. 7368
    Prev
    Next
    INDEX
    Explanations

    technical terms and metrics related to light detection and measurement

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 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
     Reverso
    -0.54
     समीक्षाओं
    -0.54
     للاسماء
    -0.50
     newBuilder
    -0.47
    IContainer
    -0.46
     Surname
    -0.45
    ItemGroup
    -0.44
    enerys
    -0.43
    例句
    -0.43
     BMD
    -0.42
    POSITIVE LOGITS
     wavelengths
    1.41
     wavelength
    1.38
    wavelength
    1.19
     Wavelength
    1.14
    Wavelength
    1.12
     spectrum
    0.99
     ultraviolet
    0.97
     espectro
    0.96
     spectral
    0.95
    spectrum
    0.91
    Activations Density 0.669%

    No Known Activations