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. 6-GEMMASCOPE-RES-16K
    6. 6472
    Prev
    Next
    INDEX
    Explanations

    terms related to queuing and data structures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 6-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_6/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.6.hook_resid_post
    Hook Layer
    6
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     AssemblyProduct
    -0.80
     conquête
    -0.71
    Хьажоргаш
    -0.70
    umman
    -0.68
    Smit
    -0.68
     sánh
    -0.67
     richesse
    -0.67
    êmio
    -0.66
    +#+
    -0.65
     INTERESAR
    -0.65
    POSITIVE LOGITS
     queue
    2.12
     Queue
    1.94
    queue
    1.93
     queues
    1.90
    Queue
    1.80
    queues
    1.63
    QUEUE
    1.60
    Queues
    1.43
     queuing
    1.41
     queued
    1.23
    Activations Density 0.051%

    No Known Activations