© 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-2-2B
    7. Residual Stream - 16k
    9. 7-GEMMASCOPE-RES-16K
    11. 12034
    Prev
    Next
    INDEX
    Explanations

    expressions related to romantic feelings and connections

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 7-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_7/width_16k/average_l0_69
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Hook Layer
    7
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    expandindo
    -1.26
    WebVitals
    -1.18
    tvguidetime
    -1.11
    AndEndTag
    -1.07
     AssemblyProduct
    -0.96
     يتيمه
    -0.94
     >=",
    -0.88
    MemoryWarning
    -0.84
    UserScript
    -0.83
     виправивши
    -0.82
    POSITIVE LOGITS
     instantly
    0.69
     impressed
    0.59
     smitten
    0.56
     innamor
    0.56
     immediately
    0.54
     onItemClick
    0.52
     captivated
    0.52
     meets
    0.51
     Instantly
    0.51
    惚
    0.49
    Activations Density 0.156%

    No Known Activations