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
    4. Residual Stream - 16k
    5. 31-GEMMASCOPE-RES-16K
    6. 16285
    Prev
    Next
    INDEX
    Explanations

    terms related to beekeeping and apiculture

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_31/width_16k/average_l0_114
    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
    BagConstraints
    -0.54
    :✨
    -0.54
    DockStyle
    -0.50
    tagHelperRunner
    -0.50
    BagLayout
    -0.49
    ConstraintMaker
    -0.48
    AccessFile
    -0.45
     JpaRepository
    -0.45
     برانيه
    -0.44
    TypedDataSet
    -0.42
    POSITIVE LOGITS
     bee
    1.28
     bees
    1.25
     honey
    1.20
     Bee
    1.13
     Bees
    1.12
     Honey
    1.07
     hive
    1.03
    Bees
    1.03
    🐝
    1.02
    Bee
    0.99
    Activations Density 0.106%

    No Known Activations