© 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. 1102
    Prev
    Next
    INDEX
    Explanations

    concepts related to ecological and climate change impacts

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

    climate and temperature increase

    np_acts-logits-general · gemini-2.0-flash

    climate change temperature increase

    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
     فريبيس
    -0.78
     correctes
    -0.66
     CommonModule
    -0.65
    SourceChecksum
    -0.65
    Carriera
    -0.63
     للمعارف
    -0.61
     refusé
    -0.58
    Portály
    -0.58
     BeautifulSoup
    -0.58
    forChild
    -0.57
    POSITIVE LOGITS
     climate
    0.84
     Climate
    0.83
    Climate
    0.82
    climate
    0.74
     future
    0.62
     klimat
    0.61
     IPCC
    0.60
     CLIMATE
    0.59
     klima
    0.58
    future
    0.57
    Activations Density 0.205%

    No Known Activations