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. 3127
    Prev
    Next
    INDEX
    Explanations

    API-related commands and HTTP request methods

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Tokens preceding URLs or URIs

    np_acts-logits-general · gemini-2.0-flash

    URLs and API endpoints

    np_acts-logits-general · gemini-2.5-flash-lite
    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
     يتيمه
    -0.72
    
    -0.53
    żer
    -0.52
     NSCoder
    -0.50
     Autorisations
    -0.50
    Населення
    -0.48
    FunctionFlags
    -0.48
    ęt
    -0.48
    Biographies
    -0.47
    MethodImpl
    -0.47
    POSITIVE LOGITS
     URL
    2.29
     url
    2.13
    URL
    2.08
    url
    2.01
     URLs
    1.92
    Url
    1.89
     Url
    1.86
     urls
    1.67
    urls
    1.46
    setUrl
    1.45
    Activations Density 0.250%

    No Known Activations