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. MLP Out - 16k
    5. 22-GEMMASCOPE-MLP-16K
    6. 15772
    Prev
    Next
    INDEX
    Explanations

    mentions of deodorizing substances and their effects on body odor

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-mlp-16k
    Configuration
    google/gemma-scope-2b-pt-mlp/layer_22/width_16k/average_l0_121
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_mlp_out
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    GEBURTSDATUM
    -0.86
    uxxxx
    -0.84
    EndInit
    -0.79
    Fns
    -0.64
    }$)
    -0.63
     otomatig
    -0.62
     Rake
    -0.60
    expandindo
    -0.59
    PreExecute
    -0.59
    posia
    -0.59
    POSITIVE LOGITS
     smell
    1.41
     smells
    1.30
     smelling
    1.27
     smelled
    1.17
     odor
    1.14
     scent
    1.13
     Smell
    1.13
     stink
    1.11
    smell
    1.09
     fragrance
    1.09
    Activations Density 0.246%

    No Known Activations