© 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-IT
    7. Residual Stream - 131k
    9. 20-GEMMASCOPE-RES-131K
    11. 79493
    Prev
    Next
    INDEX
    Explanations

    references to compassion and caring attitudes towards others

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

    compassionate and sensitive

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    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
    نش
    -0.37
     tang
    -0.35
     Lipa
    -0.34
     wander
    -0.31
    Guess
    -0.31
    IQ
    -0.31
     bosses
    -0.30
     stag
    -0.30
     Glor
    -0.30
     guess
    -0.30
    POSITIVE LOGITS
     compassionate
    0.94
     Compassion
    0.86
     compassion
    0.83
    Compassion
    0.83
     empathetic
    0.66
     caring
    0.63
     gentle
    0.60
    caring
    0.59
     sensitive
    0.58
     considerate
    0.57
    Activations Density 0.095%

    No Known Activations