© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 10-GEMMASCOPE-RES-16K
    11. 6103
    Prev
    Next
    INDEX
    Explanations

    measurements and quantities in cooking and recipe contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_10/width_16k/average_l0_113
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Sigue
    -0.45
    algo
    -0.44
     Sui
    -0.43
     Alg
    -0.42
     Algo
    -0.42
     tartalomajánló
    -0.41
     Deloitte
    -0.39
     Meno
    -0.39
     Reilly
    -0.39
     Majestic
    -0.39
    POSITIVE LOGITS
     cup
    1.97
     Cup
    1.85
    Cup
    1.84
    cup
    1.70
     cups
    1.66
     CUP
    1.64
     Cups
    1.62
    CUP
    1.47
    cups
    1.38
     taza
    1.26
    Activations Density 0.109%

    No Known Activations