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. 20-GEMMASCOPE-RES-16K
    6. 4756
    Prev
    Next
    INDEX
    Explanations

    end punctuation marks and their frequencies in text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    esez
    -0.79
    oa̍t
    -0.74
    RegistryLite
    -0.73
    الحياه
    -0.67
    تقاوى
    -0.66
    ///</
    -0.66
     invokingState
    -0.62
    RunWith
    -0.58
    DebuggerNonUser
    -0.56
     uska
    -0.55
    POSITIVE LOGITS
     ↑
    1.16
     ^
    0.92
    ]^
    0.67
    ^
    0.65
     surla
    0.61
    )^
    0.59
     Wakefield
    0.57
    новниш
    0.55
    ADVERTISEMENT
    0.54
     [*]
    0.54
    Activations Density 0.028%

    No Known Activations