© 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. 20-GEMMASCOPE-RES-16K
    11. 11961
    Prev
    Next
    INDEX
    Explanations

    information related to environmental regulations and energy efficiency measures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    energy conservation and recycling

    np_acts-logits-general · gemini-2.0-flash

    reduce energy, waste, carpooling

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     dangers
    -0.56
     Wikimedijinoj
    -0.56
    OGND
    -0.53
    ambiental
    -0.51
    bootstrapcdn
    -0.51
     danger
    -0.51
    kembangan
    -0.50
    SqlServer
    -0.49
    isks
    -0.48
    stans
    -0.48
    POSITIVE LOGITS
     retrofit
    0.76
     Reducing
    0.75
     reducing
    0.74
     reduce
    0.70
     Reduce
    0.70
    Reducing
    0.69
    principalTable
    0.68
    Reduce
    0.68
     reduction
    0.68
     Reduction
    0.68
    Activations Density 0.193%

    No Known Activations