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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 32-GEMMASCOPE-RES-131K
    6. 129923
    Prev
    Next
    INDEX
    Explanations

    instances of pity and related emotional expressions

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

    pity and sympathy

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-9b-pt-res/layer_32/width_131k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.32.hook_resid_post
    Hook Layer
    32
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    はじめに
    -0.31
     waveguide
    -0.29
    دانشنامهٔ
    -0.28
    惊
    -0.28
    veden
    -0.28
     transcur
    -0.27
     iscri
    -0.27
    喜び
    -0.27
    gew
    -0.27
     inscri
    -0.27
    POSITIVE LOGITS
     pity
    1.72
    pity
    1.51
     piti
    1.38
     Pity
    1.34
     pitiful
    1.30
     pitié
    1.24
    可怜
    1.12
     sympathy
    1.05
    Poor
    1.00
     pite
    0.98
    Activations Density 0.021%

    No Known Activations