Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 22-GEMMASCOPE-RES-16K
    6. 10925
    Prev
    Next
    INDEX
    Explanations

    phrases that discuss the health and environmental benefits of regulations and interventions

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

    preceding "benefits" or "benefit"

    np_acts-logits-general · gemini-2.0-flash

    benefits

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     AssemblyCulture
    -0.62
     pinulongan
    -0.57
    satunya
    -0.57
     weakest
    -0.56
    hebt
    -0.56
     debole
    -0.56
     ModelExpression
    -0.55
     esternos
    -0.55
    انجليز
    -0.54
    troppo
    -0.52
    POSITIVE LOGITS
     benefits
    2.58
     benefit
    2.19
    benefits
    2.12
     Benefits
    2.10
    Benefits
    2.02
     BENEFITS
    1.96
    benefit
    1.90
    Benefit
    1.86
     Benefit
    1.80
    BENEFITS
    1.77
    Activations Density 0.479%

    No Known Activations