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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 13-GEMMASCOPE-RES-16K
    6. 6721
    Prev
    Next
    INDEX
    Explanations

    keywords and phrases related to deleting or removing items in a programming context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    commands and operations related to deletion in a programming context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_13/width_16k/average_l0_84
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.13.hook_resid_post
    Hook Layer
    13
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ValueStyle
    -0.55
    ToAdd
    -0.52
    erializer
    -0.49
    parametrize
    -0.46
    PerformLayout
    -0.46
     Daß
    -0.45
    Jeografia
    -0.45
     estimés
    -0.45
    gabung
    -0.45
    AddHtmlAttribute
    -0.44
    POSITIVE LOGITS
     delete
    0.88
     removal
    0.87
     deleting
    0.87
     removals
    0.84
     removing
    0.82
    delete
    0.80
    DeleteMapping
    0.80
     deletes
    0.79
     remove
    0.78
     removes
    0.78
    Activations Density 0.129%

    No Known Activations