© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 18-GEMMASCOPE-RES-16K
    6. 7208
    Prev
    Next
    INDEX
    Explanations

    terms related to plants, particularly their characteristics and classifications

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

    "plant"

    np_acts-logits-general · gemini-2.0-flash

    plant followed by descriptor

    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
    MemoryWarning
    -0.83
    ableness
    -0.79
    cetamol
    -0.73
    WebVitals
    -0.73
    rably
    -0.71
     sulphide
    -0.69
    MockBean
    -0.69
     AssemblyCompany
    -0.67
    TypeDef
    -0.66
    TestingModule
    -0.65
    POSITIVE LOGITS
     plants
    0.73
     plant
    0.68
    Plants
    0.62
    plant
    0.61
     Plants
    0.60
     Plant
    0.57
     PLANT
    0.56
     plantas
    0.54
    PLANT
    0.54
    plants
    0.52
    Activations Density 0.180%

    No Known Activations