© 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. 22-GEMMASCOPE-RES-16K
    6. 7614
    Prev
    Next
    INDEX
    Explanations

    references to nutritional improvements and challenges in populations, particularly in relation to food security and health conditions

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

    Economic reform and development

    np_acts-logits-general · gemini-2.0-flash

    economic reforms and policy

    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
    ServletException
    -0.48
     navideñas
    -0.48
    Artist
    -0.47
     Emotions
    -0.47
     WARRANTY
    -0.45
    templateUrl
    -0.45
     artísticas
    -0.45
    titas
    -0.44
     domy
    -0.44
    ]_
    -0.43
    POSITIVE LOGITS
     reforms
    1.07
     reform
    0.96
     GDP
    0.93
     liberalization
    0.91
     Reforms
    0.90
     macroeconomic
    0.88
     IMF
    0.88
     reformers
    0.85
     reformer
    0.82
    reform
    0.82
    Activations Density 0.204%

    No Known Activations