Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 607
    Prev
    Next
    INDEX
    Explanations

    concepts related to references of divinity or supreme authority

    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
    告诉我
    -0.63
     betweenstory
    -0.60
    таратура
    -0.54
     يتيمه
    -0.54
    AddTagHelper
    -0.49
    fjspx
    -0.48
    Datuak
    -0.48
     gyhoeddwyd
    -0.47
    ftagPool
    -0.46
    
    -0.46
    POSITIVE LOGITS
     {}));
    0.67
    miyor
    0.62
     Preparations
    0.60
     preparations
    0.60
     LiveData
    0.60
     AttributeSet
    0.57
     soon
    0.56
    mişti
    0.56
     Paix
    0.56
     MonoBehaviour
    0.56
    Activations Density 0.026%

    No Known Activations