© 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. 20-GEMMASCOPE-RES-131K
    11. 87553
    Prev
    Next
    INDEX
    Explanations

    phrases that emphasize careful or intentional actions and decisions

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

    deliberate, careful, or strategic actions

    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
    NewUrlParser
    -0.39
    TSC
    -0.34
     gevaar
    -0.33
     magg
    -0.32
    asy
    -0.32
     wireType
    -0.31
     ModelExpression
    -0.31
     buoni
    -0.30
     υπό
    -0.30
    tds
    -0.30
    POSITIVE LOGITS
     carefully
    0.89
     cuidadosamente
    0.78
     soigneusement
    0.67
     Carefully
    0.67
     meticulously
    0.67
     deliberately
    0.64
    あえて
    0.63
     purposely
    0.63
     intentionally
    0.62
     strategically
    0.62
    Activations Density 0.082%

    No Known Activations