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. 12770
    Prev
    Next
    INDEX
    Explanations

    key terms and concepts related to environmental regulations and international agreements on climate change

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

    climate change and emissions

    np_acts-logits-general · gemini-2.0-flash

    carbon and emissions

    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
    Tikang
    -0.53
     nî
    -0.53
     Waterford
    -0.52
     tör
    -0.49
    Ligações
    -0.49
     <<<<<<<<<<<<<<
    -0.48
     xăm
    -0.48
     surla
    -0.48
     charmed
    -0.47
     electronically
    -0.47
    POSITIVE LOGITS
     carbon
    1.26
     Carbon
    1.13
     decarbon
    1.11
    Carbon
    1.07
    carbon
    1.05
     CARBON
    1.04
     emission
    0.98
     emissions
    0.95
     Emissions
    0.95
     karbon
    0.95
    Activations Density 0.175%

    No Known Activations