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. 2-GEMMASCOPE-RES-16K
    6. 6122
    Prev
    Next
    INDEX
    Explanations

    references to pressure in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     voltage
    -0.73
    voltage
    -0.71
     Voltage
    -0.70
     voltages
    -0.68
    invokeLater
    -0.67
    Voltage
    -0.66
     Dispens
    -0.66
     VOLTAGE
    -0.65
     detenido
    -0.64
    uega
    -0.62
    POSITIVE LOGITS
     pressure
    2.14
     Pressure
    1.96
    Pressure
    1.87
    pressure
    1.78
     PRESSURE
    1.65
     pressures
    1.43
     pressured
    1.39
     presión
    1.09
     pression
    1.05
     Druck
    0.98
    Activations Density 0.039%

    No Known Activations