© 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. 36-GEMMASCOPE-RES-16K
    11. 16270
    Prev
    Next
    INDEX
    Explanations

    words related to specific types of substances or compounds, particularly those with the "ple" or "ole" suffixes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 36-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_36/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.36.hook_resid_post
    Hook Layer
    36
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     intStringLen
    -0.54
    tonsoft
    -0.50
    afficheront
    -0.50
     Bioaccumulative
    -0.49
    stylers
    -0.49
    HandlerContext
    -0.48
    yntaxException
    -0.47
     Jefus
    -0.47
    縮
    -0.47
     Autorisations
    -0.47
    POSITIVE LOGITS
    l
    0.47
    Décès
    0.40
     Ale
    0.39
    lity
    0.38
     ALE
    0.37
    lle
    0.37
    <?
    0.37
    lse
    0.36
     Vele
    0.36
     DataTypes
    0.36
    Activations Density 0.242%

    No Known Activations