© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 2-GEMMASCOPE-RES-16K
    11. 4316
    Prev
    Next
    INDEX
    Explanations

    query parameters in URLs

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     protoimpl
    -0.91
    parsedMessage
    -0.87
    ThroughAttribute
    -0.85
    
    -0.80
    DoubleQuotes
    -0.79
    ftagPool
    -0.76
    Tazama
    -0.75
     للاسماء
    -0.71
    RTDA
    -0.71
    ScopeManager
    -0.71
    POSITIVE LOGITS
     The
    0.54
    }&
    0.51
    &
    0.49
    oggi
    0.49
    ↵↵
    0.48
    FormTagHelper
    0.47
    +"&
    0.47
    The
    0.46
    sinon
    0.43
    PointerException
    0.42
    Activations Density 0.252%

    No Known Activations