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. 2357
    Prev
    Next
    INDEX
    Explanations

    references to Bluetooth and multi-functional device compatibility

    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
    Hauptartikel
    -0.70
    بوابة
    -0.68
     houſe
    -0.68
    Portale
    -0.67
    DockStyle
    -0.66
    ValueStyle
    -0.65
    ViewFeatures
    -0.65
     Houſe
    -0.64
     raiſ
    -0.63
     pleaſure
    -0.63
    POSITIVE LOGITS
    ftagPool
    0.55
    ώρα
    0.54
    حت
    0.50
    HD
    0.46
    Suitable
    0.45
     &
    0.44
    ナン
    0.44
     brinde
    0.42
     reproducing
    0.41
    &
    0.41
    Activations Density 0.225%

    No Known Activations