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. 17-GEMMASCOPE-RES-16K
    6. 13238
    Prev
    Next
    INDEX
    Explanations

    words related to plugins and their functionality

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 17-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_17/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.17.hook_resid_post
    Hook Layer
    17
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Tikang
    -0.79
    WithIOException
    -0.73
     vectorielle
    -0.72
    ValueStyle
    -0.71
    Попис
    -0.71
     isComment
    -0.69
    spender
    -0.69
     &___
    -0.68
    Personensuche
    -0.68
    rors
    -0.67
    POSITIVE LOGITS
    plugin
    1.34
     plugins
    1.33
     PLUG
    1.33
     plug
    1.30
     plugs
    1.25
     plugin
    1.25
     Plug
    1.24
     plu
    1.22
     Plugin
    1.20
     Plugins
    1.19
    Activations Density 0.158%

    No Known Activations