Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 10733
    Prev
    Next
    INDEX
    Explanations

    terms related to virtual reality technology

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

    Virtual or augmented reality

    np_acts-logits-general · gemini-2.0-flash

    virtual reality and augmented reality

    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
     pymongo
    -0.58
     Jop
    -0.57
     SMTP
    -0.56
     Niger
    -0.56
     CWE
    -0.54
    Silen
    -0.54
    EDEFAULT
    -0.53
    SMTP
    -0.52
    BarStyle
    -0.51
    ItemBackground
    -0.50
    POSITIVE LOGITS
     VR
    1.54
     virtual
    1.38
     Virtual
    1.35
     immersive
    1.33
    VR
    1.31
    Virtual
    1.21
    virtual
    1.16
     Immer
    1.09
     Oculus
    1.07
     vr
    1.07
    Activations Density 0.232%

    No Known Activations