© 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
    7. Residual Stream - 16k
    9. 2-GEMMASCOPE-RES-16K
    11. 3718
    Prev
    Next
    INDEX
    Explanations

    references to deletion actions and commands within programming contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_2/width_16k/average_l0_67
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     him
    -0.48
     henne
    -0.44
     beliau
    -0.41
     dolayı
    -0.41
    complexContent
    -0.41
     perfección
    -0.40
    PRNewswire
    -0.40
     maternidade
    -0.40
    volvement
    -0.40
     her
    -0.40
    POSITIVE LOGITS
     delete
    1.72
    delete
    1.66
     Delete
    1.43
     deletes
    1.31
     deleting
    1.31
    Delete
    1.30
     DELETE
    1.29
     deletion
    1.27
     deleted
    1.16
    DELETE
    1.15
    Activations Density 0.107%

    No Known Activations