© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 16-GEMMASCOPE-RES-16K
    6. 9243
    Prev
    Next
    INDEX
    Explanations

    elements related to regulations and their impact on economics and society

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

    Regulations, mandates, tariffs, or burdens

    np_acts-logits-general · gemini-2.0-flash

    costs and regulatory burdens

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/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.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
    شهاد
    -0.54
    Географи
    -0.52
    temun
    -0.52
    peutic
    -0.52
    )__
    -0.52
    صح
    -0.51
    ględ
    -0.49
    "../
    -0.49
     ioutil
    -0.48
     (_)
    -0.48
    POSITIVE LOGITS
     imposed
    0.83
     burdensome
    0.80
     burden
    0.79
     onerous
    0.75
     impose
    0.73
     burdens
    0.73
     imposition
    0.69
     compliance
    0.67
     enforcement
    0.66
     restrictive
    0.60
    Activations Density 0.352%

    No Known Activations