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. 10193
    Prev
    Next
    INDEX
    Explanations

    concerns related to Michael Jackson's estate and brand integrity

    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
    ftagPool
    -0.69
     AssemblyTitle
    -0.62
    woordig
    -0.59
    Попис
    -0.58
     unforgettable
    -0.58
     userSchema
    -0.58
    ROIT
    -0.57
    참고
    -0.57
     Nowadays
    -0.56
     alltid
    -0.56
    POSITIVE LOGITS
     requested
    0.83
     tabled
    0.78
     briefing
    0.76
     clarification
    0.73
     briefed
    0.73
     submitted
    0.73
     concerns
    0.69
     clarify
    0.68
     clarified
    0.68
     letter
    0.66
    Activations Density 0.608%

    No Known Activations