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. 6538
    Prev
    Next
    INDEX
    Explanations

    phrases related to sports events and playoff qualifications

    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
    diki
    -0.50
     update
    -0.49
    Tikang
    -0.49
    ACHUSET
    -0.48
    颊
    -0.47
    gensen
    -0.46
     cor
    -0.45
    нк
    -0.45
    entwicklung
    -0.44
    Update
    -0.44
    POSITIVE LOGITS
     series
    0.93
    series
    0.86
     Series
    0.85
     SERIES
    0.82
    Series
    0.81
    SERIES
    0.73
    ſelf
    0.70
    ſelves
    0.70
    发表于
    0.68
     myſelf
    0.68
    Activations Density 0.186%

    No Known Activations