© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 9-GEMMASCOPE-RES-16K
    6. 2148
    Prev
    Next
    INDEX
    Explanations

    references to the verb "cut" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_9/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    "}")
    -0.87
    DockStyle
    -0.86
    NameValuePair
    -0.84
    complexContent
    -0.84
     Senhora
    -0.83
     pinulongan
    -0.80
    gameserver
    -0.77
    rrggbb
    -0.76
    Personensuche
    -0.75
    PositiveButton
    -0.75
    POSITIVE LOGITS
     cuts
    1.95
     CUT
    1.92
     cut
    1.87
     Cuts
    1.84
     Cut
    1.83
    cut
    1.78
    CUT
    1.76
    cuts
    1.75
    Cut
    1.71
     cutting
    1.66
    Activations Density 0.063%

    No Known Activations