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. 25-GEMMASCOPE-RES-16K
    6. 3495
    Prev
    Next
    INDEX
    Explanations

    geopolitical terms and discussions related to international relations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.hook_resid_post
    Hook Layer
    25
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     defaultstate
    -0.65
     TextInputType
    -0.60
     GoogleFonts
    -0.56
    isDebugEnabled
    -0.52
     متعلقه
    -0.51
    سطس
    -0.51
     Sikkim
    -0.50
     FetchType
    -0.49
    laß
    -0.49
    InputBorder
    -0.48
    POSITIVE LOGITS
     Ukrainian
    1.45
     Kyiv
    1.33
     Ukraine
    1.33
     Ukrainians
    1.27
    Ukrainian
    1.26
    Ukraine
    1.19
     ukrain
    1.13
     Zelensky
    1.07
     Ukra
    1.05
     ucran
    1.02
    Activations Density 0.094%

    No Known Activations