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. 10339
    Prev
    Next
    INDEX
    Explanations

    numerical values and their relations, particularly in contexts involving time, ranking, or counts

    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
    ItemBackground
    -0.62
     createStore
    -0.60
    CrossRef
    -0.58
    eraard
    -0.58
    getHost
    -0.56
    URLConnection
    -0.54
    日閲覧
    -0.53
    enumi
    -0.53
     Damit
    -0.53
    このまま
    -0.52
    POSITIVE LOGITS
     seven
    1.02
     eight
    1.00
     nine
    0.98
    seven
    0.93
     six
    0.93
     eleven
    0.90
     five
    0.90
    eight
    0.89
     four
    0.89
    six
    0.85
    Activations Density 0.467%

    No Known Activations