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. 21-GEMMASCOPE-RES-16K
    6. 741
    Prev
    Next
    INDEX
    Explanations

    phrases related to educational training and evaluation processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    HtmlAttribute
    -0.57
    
    -0.53
    dame
    -0.50
    ExtendWith
    -0.50
    جوايز
    -0.50
    Legenda
    -0.48
    BrowserModule
    -0.48
    AutoField
    -0.47
    RunWith
    -0.47
    apte
    -0.47
    POSITIVE LOGITS
     focus
    3.57
    focus
    3.12
     Focus
    2.98
    Focus
    2.94
     focuses
    2.87
     focusing
    2.84
     focused
    2.79
     concentrate
    2.60
     emphasis
    2.59
    Focusing
    2.57
    Activations Density 0.549%

    No Known Activations