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. 8-GEMMASCOPE-RES-16K
    6. 15017
    Prev
    Next
    INDEX
    Explanations

    mentions of plugins and related terminology 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 @ 8-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_8/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.8.hook_resid_post
    Hook Layer
    8
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ValueStyle
    -1.24
     CreateTagHelper
    -1.18
     BorderRadius
    -0.93
    endphp
    -0.93
     Aram
    -0.88
    Personensuche
    -0.82
    enumi
    -0.81
    Diwedd
    -0.81
    orianCalendar
    -0.81
     vectorielle
    -0.80
    POSITIVE LOGITS
     plugins
    2.03
     plugin
    2.00
    plugin
    1.99
    plugins
    1.94
     Plugin
    1.91
    Plugin
    1.89
     Plugins
    1.83
    Plugins
    1.78
     PLUG
    1.67
    PLUGIN
    1.65
    Activations Density 0.078%

    No Known Activations