© 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. 8-GEMMASCOPE-RES-16K
    6. 9797
    Prev
    Next
    INDEX
    Explanations

    phrases that inquire about names, definitions, or classifications of concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 8-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_8/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.hook_resid_post
    Hook Layer
    8
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    兌
    -0.47
    inerja
    -0.45
    getWriter
    -0.45
     />);
    -0.44
     onData
    -0.44
     ReactDOM
    -0.43
     Weise
    -0.43
    veur
    -0.43
    CardBody
    -0.43
     Tef
    -0.43
    POSITIVE LOGITS
    เรีย
    1.01
     termed
    0.98
     Called
    0.98
    Called
    0.91
     called
    0.90
     nickname
    0.90
     noemen
    0.89
     label
    0.88
     bezeichneter
    0.88
     CALLED
    0.87
    Activations Density 0.324%

    No Known Activations