© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 15-GEMMASCOPE-RES-16K
    11. 8515
    Prev
    Next
    INDEX
    Explanations

    references to remote work or home office setups

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_15/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    
    -0.63
    ValueGeneration
    -0.62
     iprot
    -0.59
    apimachinery
    -0.51
    CppCodeGen
    -0.47
     الحره
    -0.47
     estimés
    -0.46
     Layanan
    -0.46
    BeginContext
    -0.46
    항
    -0.45
    POSITIVE LOGITS
     workspace
    0.82
     laptop
    0.81
     workstation
    0.79
     laptops
    0.76
     desk
    0.74
     disambiguazione
    0.74
     workstations
    0.70
     lapto
    0.69
     sitting
    0.68
     Laptop
    0.68
    Activations Density 0.242%

    No Known Activations