© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B-IT
    7. Residual Stream - 131k
    9. 20-GEMMASCOPE-RES-131K
    11. 105400
    Prev
    Next
    INDEX
    Explanations

    chemical compounds, particularly hydrocarbons and polymers

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

    ethylene glycol, oxide, carbonate

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ⌘
    -0.49
    httphttps
    -0.38
     otor
    -0.36
     Serviço
    -0.33
     Quij
    -0.33
     kesk
    -0.32
     otorg
    -0.31
    校
    -0.31
     Did
    -0.31
     autorité
    -0.31
    POSITIVE LOGITS
    yethylene
    0.88
    phosa
    0.79
    thene
    0.74
     polyethylene
    0.73
    ene
    0.71
    ethylene
    0.71
    ylene
    0.71
    thylene
    0.69
    hloromethane
    0.69
     ethylene
    0.69
    Activations Density 0.019%

    No Known Activations