© 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. 4083
    Prev
    Next
    INDEX
    Explanations

    instances of the word "many"

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

    "Many" followed by thanks, times, years, prices

    np_acts-logits-general · gemini-2.0-flash

    many times

    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
     alguna
    -0.75
     lenker
    -0.70
     algún
    -0.69
     qualche
    -0.65
     alguma
    -0.61
     preuves
    -0.61
     kaž
    -0.61
     genoux
    -0.61
    一下
    -0.60
     négociations
    -0.60
    POSITIVE LOGITS
     different
    1.03
     thousands
    0.95
     times
    0.85
     years
    0.84
     kinds
    0.83
     hundreds
    0.80
     MANY
    0.79
    thousands
    0.79
     ways
    0.78
     millions
    0.77
    Activations Density 0.067%

    No Known Activations