© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 30-GEMMASCOPE-RES-16K
    11. 10736
    Prev
    Next
    INDEX
    Explanations

    mentions and variations of the word "carbon"

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

    "Carbon" and related chemical compounds

    np_acts-logits-general · gemini-2.0-flash

    carbon dioxide and monoxide

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 30-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_30/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.30.hook_resid_post
    Hook Layer
    30
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     vastaan
    -0.37
    SharedDtor
    -0.32
     sorun
    -0.31
     telefónica
    -0.31
     Aussch
    -0.31
     Erschein
    -0.31
     görü
    -0.30
     Wray
    -0.29
     Ausgang
    -0.29
    います
    -0.28
    POSITIVE LOGITS
    Carbon
    1.16
     Carbon
    1.08
     CARBON
    1.02
    CARBON
    0.98
    carbon
    0.94
     carbon
    0.92
     carbono
    0.82
     dioxide
    0.80
     carbone
    0.77
     karbon
    0.72
    Activations Density 0.140%

    No Known Activations