© 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. 24-GEMMASCOPE-RES-16K
    11. 14567
    Prev
    Next
    INDEX
    Explanations

    comparative terms that indicate a higher quantity or degree, especially "more."

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

    "More" followed by a comparative word

    np_acts-logits-general · gemini-2.0-flash

    more plus comparative

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     pequenas
    -0.63
     réfugi
    -0.62
     moſt
    -0.62
     noDo
    -0.62
     ótimo
    -0.61
     buenas
    -0.61
    ğraf
    -0.61
     malades
    -0.61
     buoni
    -0.60
     buone
    -0.59
    POSITIVE LOGITS
     than
    1.58
    than
    1.09
     THAN
    1.05
    Than
    1.00
     Than
    0.96
     niż
    0.92
     likely
    0.86
    THAN
    0.80
     než
    0.74
     importantly
    0.70
    Activations Density 0.160%

    No Known Activations