© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 131k
    5. 9-GEMMASCOPE-RES-131K
    6. 6043
    Prev
    Next
    INDEX
    Explanations

    references to emotions and feelings, particularly those involving sentimentality

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

    sentimental, sentiment, sentient

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_131k/average_l0_121
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Kommunikation
    -0.49
     Hukum
    -0.48
    ungguh
    -0.47
    setObject
    -0.46
    プローチ
    -0.45
    Erreferentziak
    -0.45
     interaction
    -0.45
     aider
    -0.44
    vignon
    -0.43
    Raum
    -0.43
    POSITIVE LOGITS
     sentimental
    1.58
     Senti
    1.00
    Senti
    0.91
    senti
    0.90
    IMENTAL
    0.72
     &___
    0.52
    mental
    0.52
     senti
    0.52
     nostalgic
    0.51
    PropertyChanging
    0.49
    Activations Density 0.009%

    No Known Activations