© 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
    7. Residual Stream - 16k
    9. 31-GEMMASCOPE-RES-16K
    11. 3737
    Prev
    Next
    INDEX
    Explanations

    expressions of complex emotions and relationships

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

    phrases describing emotional responses or attitudes toward people, particularly involving compassion, respect, or disdain conveyed through the preposition "with".

    oai_token-act-pair · claude-4-5-haikuTriggered by @emiglarou
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_31/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ब्रेकडाउन
    -0.50
    MERCIAL
    -0.50
     gynhyrchwyd
    -0.49
    camisetas
    -0.49
    argout
    -0.48
    thmetic
    -0.47
     تضيفلها
    -0.47
    جمعیت
    -0.46
    StoryboardSegue
    -0.46
     समीक्षाओं
    -0.46
    POSITIVE LOGITS
     hope
    0.63
     excitement
    0.62
     joy
    0.56
     satisfaction
    0.52
     love
    0.50
     pleasure
    0.49
     admiration
    0.48
     gratitude
    0.48
     dismay
    0.48
     appreciation
    0.48
    Activations Density 0.388%

    No Known Activations