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. 2753
    Prev
    Next
    INDEX
    Explanations

    instances of communication and contact within the text

    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
     <=",
    -0.91
     resourceCulture
    -0.86
     Мексичка
    -0.82
    rachtet
    -0.76
    JspWriter
    -0.76
     ExecuteAsync
    -0.74
    ValueGeneration
    -0.73
    AddTagHelper
    -0.73
     Italijanski
    -0.70
    IndentedString
    -0.70
    POSITIVE LOGITS
     asking
    1.17
     about
    1.10
     requesting
    0.93
     regarding
    0.86
    about
    0.86
     inquiring
    0.86
    asking
    0.85
     asked
    0.84
     ask
    0.82
     pregunt
    0.78
    Activations Density 0.230%

    No Known Activations