© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 31-GEMMASCOPE-RES-16K
    11. 3297
    Prev
    Next
    INDEX
    Explanations

    mentions of the word "Lot" in various contexts

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

    lot numbers and batch identifiers in scientific and technical documents.

    oai_token-act-pair · claude-4-5-haikuTriggered by @emiglarou
    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
    Tembelea
    -0.73
    TemporalType
    -0.71
    setViewportView
    -0.67
    UnusedPrivate
    -0.66
    новништво
    -0.64
     pinulongan
    -0.64
     kasarigan
    -0.63
    AndEndTag
    -0.61
    PreExecute
    -0.60
    queryInterface
    -0.60
    POSITIVE LOGITS
     Kot
    0.50
    dot
    0.50
     dot
    0.46
    spot
    0.46
     spot
    0.45
     Dot
    0.44
     Cott
    0.42
    Dot
    0.42
     SPOT
    0.41
    Kot
    0.39
    Activations Density 0.267%

    No Known Activations