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. 9207
    Prev
    Next
    INDEX
    Explanations

    expressions of relationships and social dynamics

    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
     Monfieur
    -0.78
     Jefus
    -0.76
     quæ
    -0.71
     houſe
    -0.69
     Majefty
    -0.67
    blockList
    -0.67
    ✨:
    -0.67
     ostavi
    -0.66
     Савезне
    -0.66
    WithIOException
    -0.65
    POSITIVE LOGITS
    まで
    0.51
                              
    0.45
    дже
    0.45
    puis
    0.44
    urn
    0.44
     तब
    0.43
     potentially
    0.42
     este
    0.41
     actually
    0.41
    Actually
    0.41
    Activations Density 0.152%

    No Known Activations