© 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. 15-GEMMASCOPE-RES-16K
    6. 810
    Prev
    Next
    INDEX
    Explanations

    concepts related to social and economic challenges, including references to slums and entrepreneurship

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_15/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    .
    -0.56
    ↵↵
    -0.55
    <eos>
    -0.52
    ?
    -0.49
     bestemt
    -0.47
    ;
    -0.45
    ↵
    -0.45
     The
    -0.45
     the
    -0.44
    。
    -0.44
    POSITIVE LOGITS
     ExecuteAsync
    1.14
     تانيه
    1.03
    GEBURTSDATUM
    0.95
    
    0.88
    oa̍t
    0.88
     مشين
    0.87
     الرياضيه
    0.86
    InSection
    0.85
     ligiloj
    0.85
     &___
    0.84
    Activations Density 0.853%

    No Known Activations