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-2-2B
    4. Residual Stream - 16k
    5. 12-GEMMASCOPE-RES-16K
    6. 10111
    Prev
    Next
    INDEX
    Explanations

    descriptors and qualities related to scents or fragrances

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     quæ
    -0.52
    letek
    -0.51
    tedì
    -0.49
    áñez
    -0.49
    })).
    -0.47
     recommandons
    -0.47
     vélos
    -0.46
     sabato
    -0.46
    }]
    
    -0.46
    toim
    -0.46
    POSITIVE LOGITS
     fragrance
    1.04
     fragrances
    0.91
     perfume
    0.84
     scent
    0.82
     فريبيس
    0.77
     Parfum
    0.75
     Fragrance
    0.75
     scents
    0.72
    perfume
    0.69
     perfumes
    0.69
    Activations Density 0.025%

    No Known Activations