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. 0-GEMMASCOPE-RES-16K
    6. 9788
    Prev
    Next
    INDEX
    Explanations

    terms related to naturalization and citizenship processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 0-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_0/width_16k/average_l0_105
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.hook_resid_post
    Hook Layer
    0
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     auroit
    -0.96
     feroit
    -0.94
     ainfi
    -0.93
    AccessorTable
    -0.90
     avoient
    -0.90
     myſelf
    -0.88
     étoit
    -0.88
    MemoryWarning
    -0.87
     Monfieur
    -0.86
     ivelany
    -0.86
    POSITIVE LOGITS
     natural
    1.54
     Natural
    1.46
    Natural
    1.44
    natural
    1.38
     Nature
    1.33
    自然
    1.29
     natur
    1.23
     NATURAL
    1.22
     Natur
    1.18
    Nature
    1.18
    Activations Density 0.101%

    No Known Activations