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. 10074
    Prev
    Next
    INDEX
    Explanations

    scientific methods and processes related to microscopy and immunohistochemistry

    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
     يتيمه
    -0.71
    Datuak
    -0.64
    RegressionTest
    -0.61
    ThroughAttribute
    -0.61
    مصادر
    -0.59
    SizeF
    -0.58
    istoitu
    -0.58
    脚注の使い方
    -0.55
     ControllerBase
    -0.54
    abestanden
    -0.54
    POSITIVE LOGITS
     microscope
    0.98
     microscopy
    0.96
     Microscopy
    0.92
     Microscope
    0.85
     staining
    0.78
     microscopic
    0.75
     histology
    0.74
     magnification
    0.73
     histological
    0.72
     slide
    0.71
    Activations Density 1.496%

    No Known Activations