© 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. 2-GEMMASCOPE-RES-16K
    11. 6127
    Prev
    Next
    INDEX
    Explanations

    references to the name "Lu" and its variations, along with specific terms related to 'lua' scripts and programming contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_2/width_16k/average_l0_67
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Económica
    -0.50
     betweenstory
    -0.46
     surla
    -0.44
     tertentu
    -0.43
     escalera
    -0.42
     rojas
    -0.42
     المعيارى
    -0.41
     meille
    -0.40
    MemoryWarning
    -0.40
    Література
    -0.39
    POSITIVE LOGITS
     Lu
    1.19
    Lu
    0.99
     lu
    0.94
     LU
    0.62
     Luther
    0.62
     unknownFields
    0.62
     speculation
    0.56
    lu
    0.54
    SerializedName
    0.54
    ari
    0.52
    Activations Density 0.736%

    No Known Activations