© 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. 28-GEMMASCOPE-RES-16K
    11. 8867
    Prev
    Next
    INDEX
    Explanations

    specific terms related to chemicals and their properties, particularly those associated with aerosol products

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

    Liquids, sprays, adhesives, and glues

    np_acts-logits-general · gemini-2.0-flash

    liquid and spray applications

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 28-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_28/width_16k/average_l0_119
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.28.hook_resid_post
    Hook Layer
    28
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     bordada
    -0.34
    tahankan
    -0.33
     bordados
    -0.32
    łoni
    -0.32
     vuoden
    -0.30
     casual
    -0.29
     inoxydable
    -0.28
    ayuno
    -0.28
     kahve
    -0.28
     hambre
    -0.28
    POSITIVE LOGITS
     liquid
    0.94
    liquid
    0.90
     spray
    0.90
     sprays
    0.84
    spray
    0.82
    Liquid
    0.82
     Liquid
    0.82
     sprayed
    0.81
     LIQUID
    0.77
     liquids
    0.74
    Activations Density 0.753%

    No Known Activations