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. 21-GEMMASCOPE-RES-16K
    6. 6628
    Prev
    Next
    INDEX
    Explanations

    key terms related to dimensions or measurements in technical contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    kloped
    -0.95
     propOrder
    -0.90
     الحره
    -0.89
     للاسماء
    -0.83
     ―――――
    -0.80
     initComponents
    -0.79
    resizingMask
    -0.79
    
    -0.78
     تضيفلها
    -0.77
    richTextPanel
    -0.76
    POSITIVE LOGITS
    ).
    1.80
    !).
    1.70
    .)
    1.65
    .).
    1.57
     ).
    1.48
    )。
    1.45
    ").
    1.45
    …).
    1.44
    ].
    1.43
    ...).
    1.38
    Activations Density 0.758%

    No Known Activations