© 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-2-2B
    4. Residual Stream - 16k
    5. 19-GEMMASCOPE-RES-16K
    6. 3493
    Prev
    Next
    INDEX
    Explanations

    references to various smells and odors

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 19-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_19/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Hook Layer
    19
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     <<<<<<<<<<<<<<
    -0.65
     snippetHide
    -0.60
    期刊论文
    -0.57
    Datuak
    -0.57
     Wicidata
    -0.56
    帖最后由
    -0.56
    Viitteet
    -0.56
    webElement
    -0.55
     Beattie
    -0.55
     udaler
    -0.55
    POSITIVE LOGITS
     smell
    2.36
     smells
    2.30
     smelled
    2.15
     smelling
    2.03
     scent
    1.93
    smell
    1.90
     Smell
    1.90
     odor
    1.89
    Smell
    1.87
     scents
    1.84
    Activations Density 0.146%

    No Known Activations