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. 2431
    Prev
    Next
    INDEX
    Explanations

    terms related to pumps and pumping mechanisms

    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
     Mara
    -0.73
    marginHorizontal
    -0.64
    ="<?=
    -0.64
     réf
    -0.63
     trí
    -0.62
     interiores
    -0.61
     Concordia
    -0.61
     accountId
    -0.60
     Choices
    -0.59
    Mara
    -0.58
    POSITIVE LOGITS
     pump
    2.13
     pumps
    2.05
     Pump
    2.02
    Pump
    1.99
    pump
    1.93
     PUMP
    1.91
     Pumps
    1.90
     pumped
    1.70
     pumping
    1.63
     Pumping
    1.54
    Activations Density 0.083%

    No Known Activations