© 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. 16-GEMMASCOPE-RES-16K
    6. 13645
    Prev
    Next
    INDEX
    Explanations

    references to the concept of smart technology or smart devices

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_16/width_16k/average_l0_75
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Section
    -0.35
     έκ
    -0.33
     subsequently
    -0.33
     Sheehan
    -0.33
     Section
    -0.32
    section
    -0.32
    File
    -0.32
     caballos
    -0.32
     other
    -0.31
     each
    -0.31
    POSITIVE LOGITS
     Smart
    1.46
     SMART
    1.41
    Smart
    1.38
     smart
    1.38
    smart
    1.38
    SMART
    1.35
     smartest
    1.24
     Smar
    1.18
     smarter
    1.16
     smar
    1.15
    Activations Density 0.064%

    No Known Activations