© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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-IT
    7. Residual Stream - 16k
    9. 9-GEMMASCOPE-RES-16K
    11. 4982
    Prev
    Next
    INDEX
    Explanations

    references to glass and its various forms and applications

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

    the word "glass"

    np_acts-logits-general · gemini-2.0-flash

    glass

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     OnInit
    -0.56
     hormones
    -0.47
    preneurship
    -0.45
     Rohan
    -0.44
     Vem
    -0.44
     ThemeData
    -0.44
    Maureen
    -0.43
     Hinduism
    -0.43
     spesa
    -0.43
     Teamwork
    -0.42
    POSITIVE LOGITS
     glass
    2.17
     Glass
    2.16
    glass
    2.08
    Glass
    2.06
     GLASS
    2.05
    GLASS
    1.79
     glasses
    1.50
     glas
    1.48
     Glas
    1.47
     Glasses
    1.42
    Activations Density 0.159%

    No Known Activations