© 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-2-2B
    4. Residual Stream - 65k
    5. 13-GEMMASCOPE-RES-65K
    6. 14650
    Prev
    Next
    INDEX
    Explanations

    opening tags and special tokens in structured data or programming code

    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-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_13/width_65k/average_l0_75
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    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
    er
    -1.00
    es
    -0.94
    ergies
    -0.87
    erequisites
    -0.87
    קישורים
    -0.85
    jectures
    -0.85
    RequestMethod
    -0.85
     RequestMethod
    -0.84
    zczegól
    -0.82
    Références
    -0.82
    POSITIVE LOGITS
     Kling
    0.85
    ally
    0.83
    一个
    0.81
     russes
    0.80
    leuchte
    0.80
     Kitts
    0.80
     Mühle
    0.78
    towa
    0.77
     Mariana
    0.76
    Messaging
    0.74
    Activations Density 0.075%

    No Known Activations