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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 1-GEMMASCOPE-RES-16K
    6. 13845
    Prev
    Next
    INDEX
    Explanations

    instances of the word "sent."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 1-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.1.hook_resid_post
    Hook Layer
    1
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     referenties
    -0.67
     linkovi
    -0.53
    beli
    -0.52
    databind
    -0.52
    Nazionale
    -0.50
     незавершена
    -0.50
    iprot
    -0.49
    Portály
    -0.48
    یف
    -0.48
    Przypisy
    -0.47
    POSITIVE LOGITS
     sent
    1.80
     despatched
    1.25
    sent
    1.17
     sending
    1.14
     enviado
    1.06
     Sent
    1.02
     sends
    0.99
     Sending
    0.99
    Sent
    0.96
    Sending
    0.95
    Activations Density 0.071%

    No Known Activations