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. 14258
    Prev
    Next
    INDEX
    Explanations

    requests for help or assistance

    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
    ostro
    -0.55
     BoxDecoration
    -0.52
    celot
    -0.48
     pinulongan
    -0.48
    sstil
    -0.47
    putan
    -0.47
     niyang
    -0.44
    νει
    -0.43
    ixen
    -0.43
    વ
    -0.43
    POSITIVE LOGITS
     thank
    3.71
     thanks
    3.38
     Thank
    3.34
    Thank
    3.26
    thank
    3.15
     THANK
    3.06
     Thanks
    3.06
    thanks
    3.03
     THANKS
    3.00
    Thanks
    2.99
    Activations Density 0.428%

    No Known Activations