© 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 - 65k
    9. 20-GEMMASCOPE-RES-65K
    11. 598
    Prev
    Next
    INDEX
    Explanations

    specific programming or coding contexts

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

    conjunctions and tokens that indicate relationships or conditions

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

    and/or, committed companies

    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
     Support
    -1.08
    Support
    -1.02
     supported
    -1.02
     support
    -1.00
    support
    -0.98
     SUPPORT
    -0.97
    Supporting
    -0.93
    upport
    -0.92
     Supporting
    -0.91
     supporter
    -0.90
    POSITIVE LOGITS
    tvguidetime
    0.79
    mybatisplus
    0.76
    UserScript
    0.62
    ЧИТА
    0.55
     elämä
    0.54
    setupUi
    0.54
     effectually
    0.52
    ungeon
    0.52
    EndInit
    0.52
     jäsen
    0.52
    Activations Density 0.055%

    No Known Activations