Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APISteerSAE EvalsBlog/PodcastNEWSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 5-GEMMASCOPE-RES-16K
    6. 2214
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions and notation, particularly involving derivatives and functions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Према
    -0.67
    achella
    -0.65
     whoſe
    -0.65
     Ond
    -0.65
     ſmall
    -0.64
     Verſ
    -0.64
     Theſe
    -0.63
     themſelves
    -0.63
     leaſt
    -0.62
     tromper
    -0.62
    POSITIVE LOGITS
    ^{-
    1.10
    )^{-
    1.08
    }^{-
    1.03
     }^{-
    0.92
    ]^{-
    0.81
    ^{-\
    0.76
     ^{-
    0.66
    辞典
    0.63
    ^-
    0.62
     שוליים
    0.62
    Activations Density 0.324%

    No Known Activations