© 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. 21-GEMMASCOPE-RES-16K
    11. 12279
    Prev
    Next
    INDEX
    Explanations

    scientific literature references, particularly focusing on medical and biological studies

    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
     individuality
    -0.49
    ^
    -0.48
    jek
    -0.48
     administrative
    -0.47
    coroutines
    -0.45
     PAX
    -0.44
     around
    -0.44
     separately
    -0.43
     lupo
    -0.43
    ราย
    -0.43
    POSITIVE LOGITS
    出版年
    0.99
    "];
    0.79
    "){
    0.77
    Autoritní
    0.72
    >",
    0.71
     pinulongan
    0.70
    "],
    0.70
    "]
    0.67
    CloseOperation
    0.67
    )";
    0.66
    Activations Density 0.605%

    No Known Activations