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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 5-GEMMASCOPE-RES-16K
    6. 7523
    Prev
    Next
    INDEX
    Explanations

    keywords 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 @ 5-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     htons
    -0.87
    jsxFileName
    -0.85
     ICommand
    -0.72
    WarningLevel
    -0.69
     AssemblyCulture
    -0.69
     truss
    -0.68
     Hock
    -0.68
     Roskov
    -0.68
    Lähteet
    -0.66
    iprot
    -0.66
    POSITIVE LOGITS
     delete
    1.91
    delete
    1.91
     Delete
    1.87
    Delete
    1.80
     DELETE
    1.76
     deleting
    1.72
    DELETE
    1.71
     deletes
    1.65
     deleted
    1.58
    DeleteMapping
    1.53
    Activations Density 0.064%

    No Known Activations