© 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. 12028
    Prev
    Next
    INDEX
    Explanations

    instances of the word "del" or its variations, suggesting a focus on deletion commands or related actions

    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
     telefónica
    -0.46
    AndEndTag
    -0.38
     inalámbrica
    -0.32
    对待
    -0.31
    Css
    -0.31
     الوطنية
    -0.31
     dilute
    -0.31
     Chbosky
    -0.31
    Przypisy
    -0.31
    வு
    -0.31
    POSITIVE LOGITS
    del
    2.83
     del
    2.27
    Del
    2.17
     Del
    2.16
    DEL
    1.92
     DEL
    1.80
    dels
    1.59
    deln
    1.39
    デル
    1.36
    delt
    1.19
    Activations Density 0.231%

    No Known Activations