© 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. 22-GEMMASCOPE-RES-16K
    11. 4048
    Prev
    Next
    INDEX
    Explanations

    references to quantities or amounts, particularly focusing on "more" and related comparative terms

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

    "More" followed by "than"

    np_acts-logits-general · gemini-2.0-flash

    more than

    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
     préféré
    -0.53
     <=",
    -0.51
    脚注の使い方
    -0.51
     traités
    -0.51
    
    -0.50
     dieux
    -0.50
     Roskov
    -0.50
     cérami
    -0.50
     quelli
    -0.50
     faptul
    -0.49
    POSITIVE LOGITS
     than
    1.03
    seitige
    0.76
     kinds
    0.76
     stringent
    0.72
    Brainz
    0.69
     opportunities
    0.68
     importantly
    0.66
     total
    0.66
     of
    0.66
     flexibility
    0.64
    Activations Density 0.140%

    No Known Activations