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. 10352
    Prev
    Next
    INDEX
    Explanations

    numerical references related to court proceedings

    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
     htmlFor
    -0.54
     $=\
    -0.54
     $=
    -0.54
    reda
    -0.52
    opy
    -0.50
    kháu
    -0.50
    ounted
    -0.49
    InputBorder
    -0.48
     =>
    
    -0.48
    DoubleQuotes
    -0.48
    POSITIVE LOGITS
    ГЛА
    0.72
    PRNewswire
    0.67
     Efq
    0.66
     Monfieur
    0.65
    prüche
    0.64
    󠁿
    0.64
    ApiModelProperty
    0.63
    WEBPACK
    0.63
    TagMode
    0.62
     isComment
    0.62
    Activations Density 0.181%

    No Known Activations