© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 65k
    5. 0-GEMMASCOPE-RES-65K
    6. 11629
    Prev
    Next
    INDEX
    Explanations

    HTML tags and formatting elements in a document

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 0-gemmascope-res-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_0/width_65k/average_l0_73
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    Data Type
    float32
    Hook Name
    blocks.0.hook_resid_post
    Hook Layer
    0
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Monfieur
    -0.81
     Majefty
    -0.78
     pleaſure
    -0.78
     purpoſe
    -0.75
     houſe
    -0.73
     poffe
    -0.73
     Theſe
    -0.72
     faſt
    -0.71
     ſeveral
    -0.71
     ſtate
    -0.70
    POSITIVE LOGITS
    </strong>
    0.91
    </h2>
    0.90
    </h4>
    0.86
    "]=
    0.78
    </h1>
    0.77
     kasarigan
    0.76
    ]}>
    0.76
    </u>
    0.75
    ']))
    
    0.74
    ()};
    0.73
    Activations Density 0.065%

    No Known Activations