© 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-2-2B
    7. Residual Stream - 16k
    9. 18-GEMMASCOPE-RES-16K
    11. 4516
    Prev
    Next
    INDEX
    Explanations

    references to carbon and its compounds

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

    "carbon" and related compounds

    np_acts-logits-general · gemini-2.0-flash

    carbon compounds

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Monfieur
    -0.91
     myſelf
    -0.89
     Efq
    -0.87
    MethodManager
    -0.87
    BeginContext
    -0.86
     Majefty
    -0.85
    ollectionView
    -0.80
    DockStyle
    -0.80
     poffe
    -0.79
    })*/
    -0.78
    POSITIVE LOGITS
    carbon
    0.96
     carbon
    0.94
     Carbon
    0.94
    Carbon
    0.89
    CARBON
    0.81
     CARBON
    0.75
    arbon
    0.71
     fiber
    0.61
     karbon
    0.59
     carbono
    0.58
    Activations Density 0.206%

    No Known Activations