© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 5447
    Prev
    Next
    INDEX
    Explanations

    terms related to cancer research and cell lines

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Cell types or cell lines

    np_acts-logits-general · gemini-2.0-flash

    carcinoma cells

    np_acts-logits-general · gemini-2.5-flash-lite
    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
    VersionUID
    -0.62
    UIControlState
    -0.62
     InputDecoration
    -0.62
    WaitGroup
    -0.57
    ẫ
    -0.56
     BoxDecoration
    -0.56
    SequentialGroup
    -0.56
     OMIT
    -0.55
    TemporalType
    -0.54
    Varint
    -0.53
    POSITIVE LOGITS
     cells
    0.91
     Cells
    0.75
     cultured
    0.74
     human
    0.72
     CELLS
    0.70
     cellules
    0.69
    cells
    0.69
     cell
    0.67
     transfected
    0.65
     Zellen
    0.62
    Activations Density 2.186%

    No Known Activations