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. 4296
    Prev
    Next
    INDEX
    Explanations

    occurrences of the keyword "override" in code-related 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
    sidemargin
    -0.71
    口
    -0.53
    pleen
    -0.51
    erschied
    -0.51
    netinet
    -0.50
    fcntl
    -0.50
    Personensuche
    -0.50
    tisme
    -0.49
     Sapp
    -0.49
     Alhambra
    -0.49
    POSITIVE LOGITS
    override
    2.82
     override
    1.53
     overrides
    0.99
     Override
    0.90
     Overrides
    0.89
    overrides
    0.88
     overridden
    0.86
    inheritdoc
    0.86
    OVERR
    0.79
    verride
    0.78
    Activations Density 0.015%

    No Known Activations