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. 6054
    Prev
    Next
    INDEX
    Explanations

    content related to the concept of "packing" and associated terms

    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
    setHorizontal
    -0.81
    rmt
    -0.78
     surla
    -0.77
    */].
    -0.74
     Lari
    -0.70
    发表于
    -0.67
    Τι
    -0.67
     Williams
    -0.66
     Chio
    -0.66
     Pert
    -0.66
    POSITIVE LOGITS
     Pack
    2.10
    pack
    2.06
    Pack
    2.03
     PACK
    2.03
     pack
    2.01
     packs
    1.94
    PACK
    1.90
     Packs
    1.89
    packs
    1.79
     packing
    1.74
    Activations Density 0.058%

    No Known Activations