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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 18-GEMMASCOPE-RES-16K
    11. 4123
    Prev
    Next
    INDEX
    Explanations

    characteristics related to plant breeding and growth habits

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

    Plant cultivar or hybrid names

    np_acts-logits-general · gemini-2.0-flash

    new plant varieties and breeding

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Савезне
    -0.64
    HandlerContext
    -0.62
    odymium
    -0.55
    MigrationBuilder
    -0.54
     facie
    -0.54
     Mammal
    -0.53
     ErrIntOverflow
    -0.53
    iastes
    -0.52
    Чыганаклар
    -0.51
     Jigsaw
    -0.51
    POSITIVE LOGITS
     varieties
    1.02
     cultivars
    0.96
     breeding
    0.92
     genetic
    0.91
     breed
    0.86
     cultivar
    0.85
     hybrids
    0.85
     bred
    0.85
     breeders
    0.84
     hybrid
    0.84
    Activations Density 0.488%

    No Known Activations