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. 9115
    Prev
    Next
    INDEX
    Explanations

    phrases related to future events and predictions

    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
    竟然
    -0.60
    Климат
    -0.58
     egentlig
    -0.58
     seems
    -0.57
     wydaje
    -0.57
     eigentlich
    -0.56
    了一种
    -0.55
    居然
    -0.55
    <?
    -0.53
    竟
    -0.52
    POSITIVE LOGITS
     soon
    1.02
     tomorrow
    0.98
     sooner
    0.95
     demain
    0.92
     وست
    0.91
    eventually
    0.90
     prochain
    0.90
    tomorrow
    0.87
    Soon
    0.87
     someday
    0.85
    Activations Density 0.408%

    No Known Activations