© 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-IT
    7. Residual Stream - 131k
    9. 31-GEMMASCOPE-RES-131K
    11. 20870
    Prev
    Next
    INDEX
    Explanations

    phrases related to authority and discretion in decision-making

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

    deems, wished, saw

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 31-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_31/width_131k/average_l0_109
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     MainAxisSize
    -0.41
    NSYLVANIA
    -0.35
    скур
    -0.34
    SaveChangesAsync
    -0.33
    enterOuterAlt
    -0.33
    toHaveBeenCalled
    -0.32
     náv
    -0.32
     rato
    -0.32
     NP
    -0.32
     wel
    -0.31
    POSITIVE LOGITS
     deemed
    1.98
     deem
    1.66
    deemed
    1.63
     deems
    1.59
     jugé
    1.33
    覺得
    1.23
     considered
    1.21
    觉得
    1.20
     felt
    1.19
     riten
    1.19
    Activations Density 0.194%

    No Known Activations