© 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. 20-GEMMASCOPE-RES-16K
    11. 5772
    Prev
    Next
    INDEX
    Explanations

    the word "many" and its variations, indicating a focus on quantity or abundance

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

    "Many" followed by units of time or quantity

    np_acts-logits-general · gemini-2.0-flash

    Many followed by plural entity

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     lenker
    -0.80
     algún
    -0.64
     alguna
    -0.63
    sätzlich
    -0.63
    ukone
    -0.60
     AssemblyTitle
    -0.59
    cional
    -0.58
     somehow
    -0.58
    MessageTagHelper
    -0.57
     algum
    -0.57
    POSITIVE LOGITS
     MANY
    0.92
     thousands
    0.88
    MANY
    0.86
     times
    0.83
     different
    0.78
     years
    0.76
     hundreds
    0.75
    thousands
    0.74
     millions
    0.72
     many
    0.71
    Activations Density 0.091%

    No Known Activations