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. 6713
    Prev
    Next
    INDEX
    Explanations

    specific technical terms and mechanisms related to communication systems and devices

    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
    <bos>
    -1.17
     gynhyrchwyd
    -0.69
    Personensuche
    -0.65
     pinulongan
    -0.63
    NewUrlParser
    -0.61
    []
    
    -0.60
    省市镇
    -0.59
    ]){
    
    -0.57
    getMenuInflater
    -0.55
    égias
    -0.55
    POSITIVE LOGITS
     appunto
    1.15
     refers
    1.12
     genoemd
    0.98
    と呼ばれる
    0.92
     genannt
    0.80
     bezeichnet
    0.78
    といいます
    0.77
     désigne
    0.77
    と呼ば
    0.76
     meaning
    0.73
    Activations Density 0.800%

    No Known Activations