© 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. 18-GEMMASCOPE-RES-16K
    6. 6328
    Prev
    Next
    INDEX
    Explanations

    references to variety and quantity in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Comes before description, notation, statistics

    np_acts-logits-general · gemini-2.0-flash

    some introducing descriptions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    o
    -0.52
     nogen
    -0.51
     chrétiens
    -0.50
     någon
    -0.50
     oppure
    -0.50
     jambes
    -0.49
     gră
    -0.49
    it
    -0.49
    any
    -0.49
     autorisés
    -0.49
    POSITIVE LOGITS
    '],
    
    0.85
    )"),
    0.82
    "):
    
    0.78
    ]:
    
    0.77
    '),
    
    0.76
    "]);
    
    0.76
    )");
    
    0.76
     kinds
    0.76
    >--}}
    0.75
    olesale
    0.74
    Activations Density 0.534%

    No Known Activations