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. 14247
    Prev
    Next
    INDEX
    Explanations

    references to immune system cell types and their functions

    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
    SceneManagement
    -0.53
    Filmografia
    -0.51
     >=",
    -0.51
    flashdata
    -0.50
    虚
    -0.49
     createState
    -0.48
    initComponents
    -0.48
    Արտաքին
    -0.47
    辛
    -0.46
    omock
    -0.44
    POSITIVE LOGITS
     cells
    1.65
     cell
    1.40
     Cells
    1.29
    cells
    1.26
     CELLS
    1.17
     cellules
    1.16
    ocytes
    1.15
    Cells
    1.13
     Cell
    1.09
    cell
    1.06
    Activations Density 1.236%

    No Known Activations