© 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. 4539
    Prev
    Next
    INDEX
    Explanations

    references to individuals or entities involved in claims or rumors

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

    a verb followed by "it"

    np_acts-logits-general · gemini-2.0-flash

    it as a pronoun

    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
    DoubleQuotes
    -0.85
     الحره
    -0.69
     صوتيه
    -0.64
     AssemblyCulture
    -0.63
    -------
    -0.62
    NOPQRST
    -0.61
    #
    -0.61
    RetentionPolicy
    -0.60
     doInBackground
    -0.59
    UVWXYZ
    -0.59
    POSITIVE LOGITS
     it
    2.90
    It
    1.86
     It
    1.77
    it
    1.67
    มัน
    1.15
    它
    1.08
     nó
    0.93
     آن
    0.92
     IT
    0.89
     มัน
    0.80
    Activations Density 0.649%

    No Known Activations