© 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. 10338
    Prev
    Next
    INDEX
    Explanations

    instances of the word "cool" and its variations

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

    "Cool"

    np_acts-logits-general · gemini-2.0-flash

    cool

    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
    bootstrapcdn
    -0.87
     smtplib
    -0.81
    SequentialGroup
    -0.78
    httphttps
    -0.76
    RuleContext
    -0.74
     MainAxisSize
    -0.71
     CreateTagHelper
    -0.70
    complexContent
    -0.70
    WebRequest
    -0.68
    WriteTagHelper
    -0.67
    POSITIVE LOGITS
     Cool
    1.29
     COOL
    1.26
     cool
    1.23
    Cool
    1.21
    cool
    1.19
    COOL
    1.14
     cools
    1.13
     coolest
    0.96
     cooler
    0.89
     coolness
    0.87
    Activations Density 0.047%

    No Known Activations