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. 6711
    Prev
    Next
    INDEX
    Explanations

    statements or phrases involving the act of saying or expressing something

    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
     <<<<<<<<<<<<<<
    -0.62
     ardu
    -0.59
     الحره
    -0.56
     Reine
    -0.54
    abetes
    -0.53
    évaluateur
    -0.52
     Orten
    -0.52
    商品説明
    -0.51
    通販
    -0.50
    ēj
    -0.50
    POSITIVE LOGITS
     goodbye
    1.33
     hello
    0.94
    goodbye
    0.84
     Goodbye
    0.77
     farewell
    0.74
    er
    0.71
     bye
    0.71
     aloud
    0.67
     yes
    0.66
     prayers
    0.66
    Activations Density 0.073%

    No Known Activations