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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 16k
    5. 31-GEMMASCOPE-RES-16K
    6. 16100
    Prev
    Next
    INDEX
    Explanations

    terms related to plants and gardening

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

    after "plant" or "plants"

    np_acts-logits-general · gemini-2.0-flash

    plant types and vegetation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_31/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    writeFieldEnd
    -0.59
     HasFactory
    -0.57
    AddTagHelper
    -0.54
    onAttach
    -0.51
    MessageOf
    -0.50
     ujednoznacz
    -0.49
    Autoritní
    -0.47
    setCellStyle
    -0.46
    LinkId
    -0.46
     podjela
    -0.45
    POSITIVE LOGITS
     plants
    1.36
     trees
    1.28
    trees
    1.09
     Plants
    1.07
     vegetation
    1.07
    plants
    1.06
     plant
    1.06
     plantas
    1.05
     Trees
    1.05
     tanaman
    1.05
    Activations Density 0.246%

    No Known Activations