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. 13-GEMMASCOPE-RES-16K
    6. 8816
    Prev
    Next
    INDEX
    Explanations

    markers or special symbols in the text, indicating structured data or programming elements

    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
    ']],
    -0.56
     assessment
    -0.56
    \}^{
    -0.53
     Assessment
    -0.51
    bitField
    -0.50
     rapor
    -0.49
    }`)
    -0.49
    Assessment
    -0.48
    softmax
    -0.48
     redesign
    -0.48
    POSITIVE LOGITS
    addContainerGap
    0.70
     урна
    0.69
    Географиясе
    0.64
     betweenstory
    0.61
     للمعارف
    0.59
     تضيفلها
    0.59
     pulmonar
    0.58
    примеча
    0.57
     tombé
    0.57
    ToolStripButton
    0.56
    Activations Density 0.843%

    No Known Activations