© 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. 5506
    Prev
    Next
    INDEX
    Explanations

    scientific and technical terms related to plants and legumes

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

    beans, seeds, or legumes

    np_acts-logits-general · gemini-2.0-flash

    beans and legumes

    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
     salam
    -0.72
     MainAxisSize
    -0.71
     SRT
    -0.66
    DockStyle
    -0.65
     Parac
    -0.63
    RectangleBorder
    -0.62
     pikachu
    -0.62
     Pliocene
    -0.58
     Dionys
    -0.58
     Lucre
    -0.57
    POSITIVE LOGITS
     beans
    1.23
     bean
    1.20
    bean
    1.19
     Bean
    1.18
    Bean
    1.17
     Beans
    1.16
    beans
    1.08
     legume
    1.02
    Beans
    1.01
     legumes
    0.94
    Activations Density 0.333%

    No Known Activations