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. 20-GEMMASCOPE-RES-16K
    6. 13947
    Prev
    Next
    INDEX
    Explanations

    keywords related to confocal microscopy and fluorescence imaging techniques

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    opens
    -0.52
    giau
    -0.51
     Sahne
    -0.48
     تضيفلها
    -0.46
     Audiodateien
    -0.44
     credit
    -0.43
     slat
    -0.43
     cartão
    -0.42
    Partial
    -0.42
     batter
    -0.42
    POSITIVE LOGITS
     fluorescence
    1.18
     fluorescent
    1.16
     Fluorescence
    1.09
     Fluorescent
    1.07
     fluores
    1.06
    Fluorescence
    0.99
     fluor
    0.88
     flores
    0.85
     Fluor
    0.82
    蛍
    0.81
    Activations Density 1.367%

    No Known Activations