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. 0-GEMMASCOPE-RES-16K
    6. 7806
    Prev
    Next
    INDEX
    Explanations

    mentions of communication devices or components related to receiving and transmitting signals

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 0-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_0/width_16k/average_l0_105
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.hook_resid_post
    Hook Layer
    0
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    зулта
    -0.66
    abetes
    -0.55
     seating
    -0.51
     seated
    -0.50
     الاطلاع
    -0.49
    erover
    -0.49
    Tazama
    -0.48
     Seeder
    -0.48
    قایناق‌لار
    -0.48
    ressum
    -0.48
    POSITIVE LOGITS
     receiver
    1.15
    receiver
    1.11
    Receiver
    1.10
     receivers
    1.10
     recipients
    1.00
     Receiver
    0.99
     Recipients
    0.99
    receiving
    0.98
    RECE
    0.94
     Rece
    0.92
    Activations Density 0.222%

    No Known Activations