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

    Neuronpedia

    Jacobian LensNEW
    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. 10-GEMMASCOPE-RES-16K
    11. 7866
    Prev
    Next
    INDEX
    Explanations

    function definitions related to retrieving information

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 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
     Trix
    -0.97
    
    -0.94
     fileSize
    -0.93
     userInfo
    -0.82
     itemName
    -0.80
     blockSize
    -0.78
    ősz
    -0.78
    httphttps
    -0.78
     nM
    -0.76
     isKindOfClass
    -0.76
    POSITIVE LOGITS
    get
    1.35
     get
    1.22
    Get
    1.21
     Get
    1.21
     GET
    1.19
    GET
    1.17
    Gets
    1.11
    gets
    1.02
     GETS
    1.02
     Gets
    1.00
    Activations Density 0.066%

    No Known Activations