© 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. 22-GEMMASCOPE-RES-16K
    11. 8393
    Prev
    Next
    INDEX
    Explanations

    references to individuals and their relationships

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

    Japanese particles (に, の, を, が)

    np_acts-logits-general · gemini-2.0-flash

    person referential particles

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     CreateTagHelper
    -0.95
     betweenstory
    -0.91
     BoxFit
    -0.89
    setVerticalGroup
    -0.81
    DockStyle
    -0.80
    enumi
    -0.79
    InputBorder
    -0.77
    WebVitals
    -0.75
    httphttps
    -0.74
    AutoresizingMask
    -0.73
    POSITIVE LOGITS
     için
    0.56
     द्वारा
    0.51
    ၏
    0.51
     ile
    0.46
    க்கு
    0.45
    에
    0.45
    랑
    0.45
    yla
    0.44
     által
    0.43
    ට
    0.43
    Activations Density 0.038%

    No Known Activations