© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 3-GEMMASCOPE-RES-16K
    11. 8961
    Prev
    Next
    INDEX
    Explanations

    elements and functions related to event handling and HTML structure in programming documentation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    TagMode
    -0.94
     متعلقه
    -0.84
    +#+
    -0.79
    bootstrapcdn
    -0.77
    TagHelper
    -0.74
    VIAF
    -0.73
    AndEndTag
    -0.72
     mergeFrom
    -0.72
     للاسماء
    -0.71
     itſelf
    -0.70
    POSITIVE LOGITS
     CreateTagHelper
    1.11
    setState
    0.96
    OnClickListener
    0.88
     EventArgs
    0.81
    </thead>
    0.80
     useState
    0.76
    construct
    0.74
    useState
    0.72
    ResumeLayout
    0.69
     axios
    0.61
    Activations Density 0.008%

    No Known Activations