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. 11624
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to farewells and endings

    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
    didSet
    -0.49
    openzeppelin
    -0.49
     expansión
    -0.46
     autorytatywna
    -0.46
    ImageContext
    -0.46
     sement
    -0.44
    specialchars
    -0.44
     expansion
    -0.44
    dolu
    -0.44
    tivité
    -0.43
    POSITIVE LOGITS
     goodbye
    1.47
     farewell
    1.45
    Farewell
    1.31
     Goodbye
    1.31
    Goodbye
    1.25
    goodbye
    1.22
     adieu
    1.20
     parting
    1.20
     Farewell
    1.19
    byes
    1.15
    Activations Density 0.113%

    No Known Activations