© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 4-GEMMASCOPE-RES-16K
    6. 12837
    Prev
    Next
    INDEX
    Explanations

    terms related to plants and their applications in medicine and agriculture

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.hook_resid_post
    Hook Layer
    4
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    fjspx
    -0.51
    SourceChecksum
    -0.51
    LabelTagHelper
    -0.50
    IFICATIONS
    -0.50
    omock
    -0.47
     Hentet
    -0.45
     Приступљено
    -0.45
    phens
    -0.44
     sitesinde
    -0.44
    ensively
    -0.44
    POSITIVE LOGITS
     plant
    1.15
     plants
    1.13
     Plants
    1.09
    Plants
    1.07
     Plant
    1.05
     flora
    1.04
     PLANTS
    1.02
    Plant
    0.99
     plantes
    0.97
     PLANT
    0.94
    Activations Density 0.465%

    No Known Activations