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. 0-GEMMASCOPE-RES-16K
    6. 32
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word 'slip' and references to standard data types or fields related to input forms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 0-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_0/width_16k/average_l0_105
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.hook_resid_post
    Hook Layer
    0
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ФО
    -0.50
    
    -0.50
     Khanna
    -0.49
     nigra
    -0.49
     fiel
    -0.48
     сути
    -0.47
    AuthContext
    -0.46
    ListModule
    -0.45
    リコン
    -0.45
     رق
    -0.44
    POSITIVE LOGITS
    istoitu
    0.88
     Xiao
    0.80
    archiviato
    0.78
     Reverse
    0.77
    complexContent
    0.76
    stdc
    0.76
     reverse
    0.76
     backwards
    0.76
    reverse
    0.76
     ویکی‌پدیای
    0.74
    Activations Density 0.130%

    No Known Activations