© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 7758
    Prev
    Next
    INDEX
    Explanations

    commands and functions related to creating rules and policies in programming contexts

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

    Code syntax: parentheses, semicolons, and operators

    np_acts-logits-general · gemini-2.0-flash

    create

    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
    endphp
    -0.62
     pinulongan
    -0.54
    ########.
    -0.54
    ougou
    -0.53
    ensus
    -0.52
     istanbul
    -0.52
     betweenstory
    -0.49
     Vaugh
    -0.49
     Warszawie
    -0.48
     <=",
    -0.48
    POSITIVE LOGITS
     CREAT
    2.14
     creation
    2.06
     cré
    2.02
     Creation
    2.01
     create
    1.95
    create
    1.92
     CREATE
    1.89
    Creation
    1.89
     creat
    1.87
     Create
    1.86
    Activations Density 0.131%

    No Known Activations