© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 131k
    9. 20-GEMMASCOPE-RES-131K
    11. 104134
    Prev
    Next
    INDEX
    Explanations

    phrases indicative of sitting or remaining in a location, often in a state of inactivity or waiting

    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
     poursuite
    -0.41
    engagent
    -0.40
     thereto
    -0.40
    ፩
    -0.40
     tourisme
    -0.39
    SUCCEEDED
    -0.39
     memas
    -0.38
     soon
    -0.38
    expliquer
    -0.38
     déplacement
    -0.38
    POSITIVE LOGITS
     sitting
    0.72
    sitting
    0.68
    躇
    0.65
     sits
    0.61
     idle
    0.59
     برانيه
    0.59
     idly
    0.59
     Sitting
    0.59
     sitter
    0.58
    Sitting
    0.57
    Activations Density 0.017%

    No Known Activations