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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 10-GEMMASCOPE-RES-16K
    6. 11727
    Prev
    Next
    INDEX
    Explanations

    terms related to virtual communication and online learning environments

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Савезне
    -0.67
    SpringRunner
    -0.64
     betweenstory
    -0.63
    sizeCache
    -0.59
    CppCodeGen
    -0.59
    DotNetBar
    -0.58
     مشين
    -0.57
    ActionButton
    -0.56
    buttonBar
    -0.56
     CreateTagHelper
    -0.56
    POSITIVE LOGITS
     online
    1.05
     virtual
    1.03
     Virtual
    0.94
     Online
    0.93
    Online
    0.90
    Virtual
    0.88
    online
    0.88
     VIRTUAL
    0.86
    virtual
    0.85
     Zoom
    0.84
    Activations Density 0.238%

    No Known Activations