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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 105552
    Prev
    Next
    INDEX
    Explanations

    expressions of seeking companionship and meaningful relationships

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Language expressing desire for a relationship partner with specific qualities, typically using phrases like "want someone who" or "find someone who can" followed by desired relationship traits like "love", "respect", and phrases about shared future together such as "be with for life" or "make each other feel" certain emotions.

    eleuther_acts_top20 · claude-3-7-sonnet-20250219Triggered by @lu-christina
    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
    BufferException
    -0.59
    Jeografia
    -0.51
    ViewFeatures
    -0.46
    injected
    -0.44
    Conflict
    -0.43
    brush
    -0.42
     Rptr
    -0.42
    aneo
    -0.42
    czegó
    -0.42
    cool
    -0.41
    POSITIVE LOGITS
    enumi
    0.50
    TagMode
    0.42
     exclusivos
    0.38
    lijkheid
    0.36
     SimpleName
    0.35
    ceğine
    0.34
     libertad
    0.34
    𝟹
    0.34
    addValue
    0.34
     love
    0.33
    Activations Density 0.049%

    No Known Activations