© 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. 20-GEMMASCOPE-RES-16K
    6. 9961
    Prev
    Next
    INDEX
    Explanations

    terms related to urban planning and infrastructure development

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_16k/average_l0_68
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     lắm
    -0.35
     égard
    -0.29
     suele
    -0.28
     types
    -0.27
     conoscenza
    -0.27
     mennes
    -0.26
     rå
    -0.25
     excès
    -0.24
     diferite
    -0.24
     wszel
    -0.23
    POSITIVE LOGITS
     disambiguazione
    0.91
    MLLoader
    0.88
    Tembelea
    0.75
     nahilalakip
    0.74
     للمعارف
    0.74
    astéro
    0.72
    ロウィン
    0.72
    estrian
    0.71
     صوتيه
    0.70
    Tikang
    0.69
    Activations Density 0.247%

    No Known Activations