© 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. 40-GEMMASCOPE-RES-16K
    11. 5025
    Prev
    Next
    INDEX
    Explanations

    terms related to chemical stability and degradation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 40-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_40/width_16k/average_l0_125
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.40.hook_resid_post
    Hook Layer
    40
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ünsche
    -0.41
     merke
    -0.39
     समीक्षाओं
    -0.37
     Pend
    -0.36
    orszá
    -0.35
     Banjar
    -0.34
    ernoo
    -0.34
     registration
    -0.33
     Regulation
    -0.33
     tré
    -0.33
    POSITIVE LOGITS
     degradation
    1.73
     decomposition
    1.68
     Degradation
    1.59
     degrade
    1.54
     degra
    1.54
     decompose
    1.52
     decom
    1.51
     degrad
    1.48
     Decomposition
    1.48
     degrading
    1.48
    Activations Density 1.493%

    No Known Activations