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. 16-GEMMASCOPE-RES-16K
    6. 16145
    Prev
    Next
    INDEX
    Explanations

    commands and functions related to project management and testing software

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    sizeCache
    -0.69
    abstractmethod
    -0.66
    expandindo
    -0.63
    ])]
    -0.62
    )),
    
    -0.59
    InjectAttribute
    -0.59
    تقاوى
    -0.59
    httphttps
    -0.58
    })*/
    -0.57
    %");
    -0.57
    POSITIVE LOGITS
    DockStyle
    0.61
    NewLabel
    0.53
     Lalu
    0.53
     fince
    0.51
    posób
    0.51
     tibet
    0.51
    untitled
    0.50
     Jefus
    0.50
    letics
    0.49
     EconPapers
    0.49
    Activations Density 0.268%

    No Known Activations