Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 22-GEMMASCOPE-RES-16K
    6. 10309
    Prev
    Next
    INDEX
    Explanations

    terms related to seed cultivation and plant growth processes

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

    Farming, gardening, and growing plants

    np_acts-logits-general · gemini-2.0-flash

    gardening and cultivation topics

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     civilian
    -0.55
    präsident
    -0.54
     Travelers
    -0.53
     Swallow
    -0.52
     civilians
    -0.50
     Civilian
    -0.49
     Reverso
    -0.49
    MigrationBuilder
    -0.48
     Kamin
    -0.48
    mybatisplus
    -0.47
    POSITIVE LOGITS
     potting
    0.72
     watering
    0.67
     transplanting
    0.65
     hydropon
    0.63
     pots
    0.63
     fertig
    0.62
     Watering
    0.62
     greenhouse
    0.61
     grow
    0.58
     vermic
    0.58
    Activations Density 0.185%

    No Known Activations