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. 12060
    Prev
    Next
    INDEX
    Explanations

    links to online documents and resources related to technology and programming documentation

    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
     Jefus
    -0.96
     pleaſure
    -0.95
     itſelf
    -0.95
     myſelf
    -0.95
     Efq
    -0.93
     Monfieur
    -0.91
     uſed
    -0.90
     houſe
    -0.89
     $_"
    -0.89
     purpoſe
    -0.87
    POSITIVE LOGITS
    rungsseite
    0.71
    '
    0.69
    .
    0.68
     kasarigan
    0.64
     دیکھیے
    0.63
    GEBURTSDATUM
    0.63
    ’
    0.62
     Insee
    0.61
    <bos>
    0.59
    ,
    0.58
    Activations Density 3.670%

    No Known Activations