© 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. 111137
    Prev
    Next
    INDEX
    Explanations

    phrases related to being excluded or out of a situation

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

    out of

    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
     ainfi
    -0.87
     vectorielle
    -0.69
     zoude
    -0.67
     móvel
    -0.65
     dezelve
    -0.64
     quelcon
    -0.64
     fédé
    -0.63
     suivante
    -0.62
    retudo
    -0.62
     salaire
    -0.62
    POSITIVE LOGITS
     out
    1.23
     Out
    1.20
     OUT
    1.17
    Out
    1.16
    out
    1.11
    OUT
    0.93
    EOUT
    0.93
     outs
    0.81
     Hout
    0.79
    outs
    0.79
    Activations Density 0.059%

    No Known Activations