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. 2752
    Prev
    Next
    INDEX
    Explanations

    references to blessings and curses in relation to obedience and disobedience

    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
     Belf
    -0.50
    skeleton
    -0.49
     bob
    -0.42
    Chham
    -0.42
     Buddhist
    -0.42
    ierende
    -0.41
     kertas
    -0.41
    Turk
    -0.41
    Sql
    -0.40
     Deane
    -0.40
    POSITIVE LOGITS
     CreateTagHelper
    1.07
    aarrggbb
    0.98
    webElementXpaths
    0.86
    AnchorStyles
    0.86
     Exodus
    0.84
    脚注の使い方
    0.81
    Exodus
    0.78
    rrggbb
    0.76
     Moses
    0.75
     Pharaoh
    0.73
    Activations Density 0.103%

    No Known Activations