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-2-9B
    4. Residual Stream - 16k
    5. 21-GEMMASCOPE-RES-16K
    6. 12142
    Prev
    Next
    INDEX
    Explanations

    references to significant events or actions related to law enforcement and political dissent

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_21/width_16k/average_l0_129
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     duplo
    -0.35
     attentes
    -0.34
     relatifs
    -0.33
     générations
    -0.33
     yanı
    -0.33
     chercheurs
    -0.33
     circonstances
    -0.33
     goûts
    -0.32
     ilgi
    -0.32
     research
    -0.31
    POSITIVE LOGITS
     propOrder
    0.97
    хьтан
    0.90
    lawayo
    0.71
    webElementXpaths
    0.70
    Zimbabwe
    0.70
     Harare
    0.66
    UnsafeEnabled
    0.65
    onedDateTime
    0.65
     Zimbabwe
    0.64
     dAtA
    0.64
    Activations Density 0.092%

    No Known Activations