© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 10-GEMMASCOPE-RES-16K
    6. 7538
    Prev
    Next
    INDEX
    Explanations

    LaTeX package names commonly used for mathematical typesetting and graphical inclusion

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_10/width_16k/average_l0_113
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    CrossRef
    -1.27
    AutoSize
    -0.72
     <!--
    -0.60
     informée
    -0.59
     linkovi
    -0.57
    PREFERRED
    -0.56
    Sucesor
    -0.54
    HtmlAttribute
    -0.54
    YourGuide
    -0.54
    makeText
    -0.53
    POSITIVE LOGITS
    ="+
    2.27
    ='+
    1.35
    ='"+
    1.13
    amssymb
    1.09
    /"+
    1.07
    >"+
    1.06
    AppCompat
    1.05
     "+
    1.02
    "+
    1.02
    -"+
    1.02
    Activations Density 0.012%

    No Known Activations