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. 11-GEMMASCOPE-RES-16K
    6. 6342
    Prev
    Next
    INDEX
    Explanations

    references to plugins in a technical context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Hook Layer
    11
    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
    -1.21
    ValueStyle
    -1.14
     BorderRadius
    -1.01
     vectorielle
    -0.90
     Aram
    -0.89
    Tikang
    -0.87
    Odkazy
    -0.81
    Viitteet
    -0.81
     كومونز
    -0.81
    ChildScrollView
    -0.80
    POSITIVE LOGITS
    plugin
    1.86
     plugins
    1.83
     plugin
    1.83
     Plugin
    1.76
    Plugin
    1.75
    plugins
    1.74
     PLUG
    1.65
     Plugins
    1.65
    Plugins
    1.59
    PLUGIN
    1.54
    Activations Density 0.086%

    No Known Activations