Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 21-GEMMASCOPE-RES-16K
    6. 7634
    Prev
    Next
    INDEX
    Explanations

    references to washing machines and their maintenance

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_21/width_16k/average_l0_129
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     jembatan
    -0.43
    ptonshire
    -0.43
    CONCLUSIONES
    -0.42
     puente
    -0.37
     vytvoř
    -0.36
     emplois
    -0.36
     gevaar
    -0.36
     akik
    -0.35
     véhicules
    -0.35
    Conclusie
    -0.35
    POSITIVE LOGITS
     machine
    0.82
    一台
    0.73
     machines
    0.73
     propOrder
    0.73
     appliance
    0.73
    AndEndTag
    0.72
     Appliance
    0.66
     máquina
    0.65
     device
    0.65
    machine
    0.63
    Activations Density 0.667%

    No Known Activations