© 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. 55867
    Prev
    Next
    INDEX
    Explanations

    ingredients and instructions related to cooking or recipes

    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
     would
    -0.45
     fast
    -0.45
    范
    -0.44
    뿐
    -0.44
    Fast
    -0.44
    fast
    -0.43
    </h5>
    -0.43
     may
    -0.42
     when
    -0.42
     is
    -0.42
    POSITIVE LOGITS
    
    1.00
    URLException
    0.95
     EClass
    0.91
    /**
    0.89
    apimachinery
    0.87
    MigrationBuilder
    0.82
     &___
    0.81
    structors
    0.79
    principalColumn
    0.79
     ModelExpression
    0.79
    Activations Density 0.007%

    No Known Activations