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. 702
    Prev
    Next
    INDEX
    Explanations

    text related to copying and licensing software, specifically permissions and obtaining copies

    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
    uxxxx
    -0.56
    }))
    
    -0.52
    charCodeAt
    -0.48
     tả
    -0.48
     Paglinawan
    -0.47
    [...,
    -0.46
     autorytatywna
    -0.45
    onomía
    -0.45
    RTLD
    -0.45
    tanooga
    -0.45
    POSITIVE LOGITS
     copy
    2.77
     copies
    2.65
    copy
    2.45
     Copy
    2.42
     copie
    2.32
    Copy
    2.30
     Copies
    2.25
    copies
    2.23
     copied
    2.22
     copia
    2.17
    Activations Density 0.344%

    No Known Activations