Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsBlogSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 4857
    Prev
    Next
    INDEX
    Explanations

    references to the concept of "pressure" and its various sources or effects in contexts such as societal, political, or personal situations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_131k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     unterscheidet
    -0.35
     class
    -0.33
    毫无
    -0.31
     without
    -0.31
     folha
    -0.31
     complete
    -0.30
    gaande
    -0.30
    ⚭
    -0.30
    ensement
    -0.30
    我认为
    -0.30
    POSITIVE LOGITS
    pressure
    1.16
     pressure
    1.15
    Pressure
    1.09
     Pressure
    1.08
     PRESSURE
    1.07
     pressured
    1.01
     pressures
    0.98
     presión
    0.93
     pression
    0.90
     pressão
    0.83
    Activations Density 0.019%

    No Known Activations