Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 7-GEMMASCOPE-RES-16K
    6. 14646
    Prev
    Next
    INDEX
    Explanations

    instances of the word "delete" and variations related to deletion operations in programming contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 7-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_7/width_16k/average_l0_69
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Hook Layer
    7
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     AssemblyCulture
    -0.82
    jsxFileName
    -0.80
    OrBuilder
    -0.78
     htons
    -0.76
    Lähteet
    -0.72
     ICommand
    -0.71
     Roskov
    -0.71
    labus
    -0.70
    CharStream
    -0.69
    ynchrotron
    -0.69
    POSITIVE LOGITS
     Delete
    1.56
     delete
    1.50
    Delete
    1.46
     DELETE
    1.45
    delete
    1.42
     deleting
    1.37
     Deletes
    1.36
     deletes
    1.35
    DELETE
    1.32
     deleted
    1.29
    Activations Density 0.040%

    No Known Activations