© 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 - 65k
    9. 20-GEMMASCOPE-RES-65K
    11. 241
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "by" in various contexts

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

    the word "by" in various contexts

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

    by followed by virtue

    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-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_65k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    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
     Shakspeare
    -0.76
     Cæsar
    -0.74
     Mahomet
    -0.69
     Shaksp
    -0.68
     Spinoza
    -0.65
     Chriftian
    -0.64
     Anſ
    -0.64
     Sarm
    -0.63
     Oedipus
    -0.62
     Reſ
    -0.61
    POSITIVE LOGITS
    standers
    1.23
     the
    1.08
     virtue
    1.04
    stander
    1.03
     means
    0.95
     a
    0.92
     way
    0.87
     an
    0.86
    ]='\
    0.81
     default
    0.81
    Activations Density 0.293%

    No Known Activations