© 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. 9-GEMMASCOPE-RES-16K
    6. 9874
    Prev
    Next
    INDEX
    Explanations

    references to surface area and spatial measurements in ecological contexts

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

    The neuron detects area measurements in scientific notation, particularly square meters (m²) and hectares (ha) with their associated numeric values.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_9/width_16k/average_l0_100
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    CloseOperation
    -0.52
     sekali
    -0.48
     direção
    -0.46
     setelan
    -0.44
     sumpay
    -0.43
    HomeAsUpEnabled
    -0.42
    öhne
    -0.42
    ibatkan
    -0.40
    extré
    -0.40
     plomo
    -0.40
    POSITIVE LOGITS
     area
    0.90
    面積
    0.85
    面积
    0.83
    Area
    0.76
    area
    0.76
     Area
    0.76
     Fläche
    0.71
     área
    0.69
     AREA
    0.68
    AREA
    0.67
    Activations Density 0.284%

    No Known Activations