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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 28-GEMMASCOPE-RES-16K
    6. 7142
    Prev
    Next
    INDEX
    Explanations

    components associated with software or programming terms

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

    "Ceylon" or related to Sri Lanka

    np_acts-logits-general · gemini-2.0-flash

    Ceylon Spinach

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 28-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_28/width_16k/average_l0_119
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.28.hook_resid_post
    Hook Layer
    28
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     argint
    -0.50
     mexicanos
    -0.48
     tacón
    -0.45
    México
    -0.41
     México
    -0.39
     calientes
    -0.39
     mexicano
    -0.39
     canadensis
    -0.39
     Mexican
    -0.38
    QSize
    -0.38
    POSITIVE LOGITS
     Ceylon
    0.93
     Colombo
    0.85
     Sri
    0.82
     Lanka
    0.81
     Sinh
    0.74
     Lankan
    0.73
    Sri
    0.71
     lanka
    0.71
     Kandy
    0.66
     sri
    0.65
    Activations Density 0.047%

    No Known Activations