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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & 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. 9277
    Prev
    Next
    INDEX
    Explanations

    specific instances of physical actions and their results in a sports context

    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
     diario
    -0.68
     daily
    -0.65
     oldValue
    -0.57
    Nowadays
    -0.57
     quotidien
    -0.55
    aujourd
    -0.55
     "<?
    -0.54
    每天
    -0.53
     Nowadays
    -0.53
    毎日
    -0.53
    POSITIVE LOGITS
    Moments
    0.59
     ensuing
    0.57
     moments
    0.57
     Moments
    0.56
     momentarily
    0.55
     soon
    0.54
    moments
    0.54
     consecutive
    0.52
    المناصب
    0.52
     shortly
    0.52
    Activations Density 0.135%

    No Known Activations