© 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-2-9B
    7. Residual Stream - 16k
    9. 3-GEMMASCOPE-RES-16K
    11. 9064
    Prev
    Next
    INDEX
    Explanations

    elements of text formatting or styling tags

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_3/width_16k/average_l0_90
    Prompts (Dashboard)
    24,576 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
     betweenstory
    -0.89
     queſta
    -0.89
    MLLoader
    -0.85
     MainAxisSize
    -0.83
     
    -0.83
    ValueStyle
    -0.71
     disambiguazione
    -0.70
     DBNull
    -0.70
    PerformLayout
    -0.69
     desmotivaciones
    -0.69
    POSITIVE LOGITS
    <em>
    3.17
    <i>
    2.34
    <strong>
    1.50
    <u>
    1.33
    <b>
    1.23
    <code>
    1.21
    </em>
    1.05
    /*
    0.94
    <sub>
    0.94
    <sup>
    0.91
    Activations Density 0.034%

    No Known Activations