© 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. 1-GEMMASCOPE-RES-16K
    6. 10888
    Prev
    Next
    INDEX
    Explanations

    references to numerical identifiers, especially ordinal numbers

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 1-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.1.hook_resid_post
    Hook Layer
    1
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     становника
    -0.62
    "],
    
    -0.61
     Faso
    -0.60
    Behaviors
    -0.60
    abrigo
    -0.59
    (['/
    -0.59
     Progression
    -0.58
     Breda
    -0.58
    UTERS
    -0.57
    σθαι
    -0.57
    POSITIVE LOGITS
     Fifth
    1.07
     Second
    1.06
     Fourth
    1.01
     Seventh
    0.98
     Third
    0.98
    Fifth
    0.96
    Second
    0.91
     Ninth
    0.91
    Fourth
    0.88
    Third
    0.87
    Activations Density 0.104%

    No Known Activations