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. 12415
    Prev
    Next
    INDEX
    Explanations

    specific command or function actions in programming contexts

    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
     Daniel
    -0.55
     Samuel
    -0.54
     Farr
    -0.52
    uku
    -0.51
    hana
    -0.50
     Вікіпе
    -0.48
     ad
    -0.47
    ль
    -0.47
    ُّ
    -0.47
     Ang
    -0.47
    POSITIVE LOGITS
     дописавши
    0.78
     विश्वसनीयता
    0.75
    }}}}
    0.72
     CreateTagHelper
    0.67
    aarrggbb
    0.67
    IndentedString
    0.65
    _))
    0.65
    ConstraintMaker
    0.65
    ])))
    0.64
     تانيه
    0.64
    Activations Density 0.071%

    No Known Activations