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. 9178
    Prev
    Next
    INDEX
    Explanations

    phrases related to legal and regulatory matters

    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
     then
    -1.09
     dann
    -1.02
     Then
    -0.98
    eventually
    -0.95
    Then
    -0.94
     Eventually
    -0.94
    then
    -0.94
     later
    -0.94
     eventually
    -0.92
     Later
    -0.91
    POSITIVE LOGITS
     currently
    1.25
    currently
    1.19
     now
    1.11
     presently
    1.09
     actuellement
    1.05
    Currently
    1.02
     Currently
    1.01
     derzeit
    1.00
     atm
    1.00
     сейчас
    0.93
    Activations Density 0.516%

    No Known Activations