© 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. 18-GEMMASCOPE-RES-16K
    11. 364
    Prev
    Next
    INDEX
    Explanations

    connections related to environmental and health regulations

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

    Regulations, sections, and parts

    np_acts-logits-general · gemini-2.0-flash

    EPA regulations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ExecuteReader
    -0.50
     stolen
    -0.47
     dég
    -0.45
    Swish
    -0.45
     arru
    -0.43
     курс
    -0.43
    eber
    -0.42
    tagHelper
    -0.42
    soldiers
    -0.42
    steal
    -0.42
    POSITIVE LOGITS
    存于互联网档案馆
    0.84
    SequentialGroup
    0.75
     permittee
    0.72
     חיצוניים
    0.71
     BoxFit
    0.69
     getRule
    0.69
     epa
    0.67
    seamnă
    0.67
     Мексичка
    0.66
     fubject
    0.66
    Activations Density 0.077%

    No Known Activations