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. 1-GEMMASCOPE-RES-16K
    6. 6114
    Prev
    Next
    INDEX
    Explanations

    references to the term "minor" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 1-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.1.hook_resid_post
    Hook Layer
    1
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     big
    -0.61
     large
    -0.56
     mega
    -0.55
    mega
    -0.53
     Big
    -0.53
     utafitiHapana
    -0.48
     huge
    -0.47
     Max
    -0.47
    ...
    -0.46
     democrá
    -0.46
    POSITIVE LOGITS
     minor
    4.21
    minor
    3.94
    Minor
    3.90
     Minor
    3.84
     MINOR
    3.48
    MINOR
    2.95
     minors
    2.61
     mineures
    2.00
     minore
    1.86
     minori
    1.77
    Activations Density 0.109%

    No Known Activations