© 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. 10-GEMMASCOPE-RES-16K
    11. 12952
    Prev
    Next
    INDEX
    Explanations

    mentions of buildings and architectural structures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 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
     iconst
    -0.57
     Hickman
    -0.54
    EndContext
    -0.54
    forChild
    -0.51
     Schla
    -0.49
    Collegamenti
    -0.49
     lenker
    -0.49
     Unwin
    -0.49
     pauv
    -0.48
    脚注の使い方
    -0.48
    POSITIVE LOGITS
     lease
    0.69
     كورة
    0.68
     AssemblyTitle
    0.66
     leased
    0.65
     office
    0.62
     Lease
    0.62
    office
    0.62
     occup
    0.61
     tenant
    0.61
     arrend
    0.60
    Activations Density 0.082%

    No Known Activations