© 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 - 65k
    5. 0-GEMMASCOPE-RES-65K
    6. 10313
    Prev
    Next
    INDEX
    Explanations

    references to bears, specifically teddy bears and bear-related motifs

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 0-gemmascope-res-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_0/width_65k/average_l0_73
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    Data Type
    float32
    Hook Name
    blocks.0.hook_resid_post
    Hook Layer
    0
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    fromnode
    -0.76
     AssemblyVersion
    -0.72
    Referències
    -0.67
    addGap
    -0.65
     Drapeau
    -0.65
     iParam
    -0.63
     Jacek
    -0.63
    alot
    -0.62
     Nacho
    -0.62
    SetBool
    -0.61
    POSITIVE LOGITS
     bear
    0.99
    Bear
    0.82
     Bear
    0.82
    bear
    0.79
     BEAR
    0.75
     bus
    0.74
    Bus
    0.71
     Bus
    0.71
    bus
    0.71
     bears
    0.65
    Activations Density 0.066%

    No Known Activations