© 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 - 16k
    5. 4-GEMMASCOPE-RES-16K
    6. 1236
    Prev
    Next
    INDEX
    Explanations

    references to equality or equal treatment in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.hook_resid_post
    Hook Layer
    4
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    "):
    
    -0.81
     Kaye
    -0.74
    "]);
    
    -0.71
    )");
    
    -0.69
    ProgressHUD
    -0.67
    Pyx
    -0.67
    ]--;
    -0.64
    vertx
    -0.63
     "");
    
    -0.63
    ]:
    
    -0.63
    POSITIVE LOGITS
     equal
    2.32
     Equal
    2.16
    equal
    2.05
    Equal
    2.03
     EQUAL
    1.99
    EQUAL
    1.76
     égal
    1.69
     equals
    1.67
     égale
    1.49
     equality
    1.44
    Activations Density 0.076%

    No Known Activations