© 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. 7-GEMMASCOPE-RES-16K
    6. 6776
    Prev
    Next
    INDEX
    Explanations

    mentions of sports teams or events, particularly in the context of playoff performance

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    references to hockey tournaments and playoff series

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 7-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_7/width_16k/average_l0_69
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Hook Layer
    7
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    TemporalType
    -0.60
    fjspx
    -0.53
    ILayout
    -0.53
    +#+#
    -0.50
     pardon
    -0.49
     nakalista
    -0.48
    SpringBootTest
    -0.48
    XmlType
    -0.47
    gemeester
    -0.47
    FailureListener
    -0.47
    POSITIVE LOGITS
     EconPapers
    0.76
     ligiloj
    0.61
    Geplaatst
    0.60
     postseason
    0.59
     JADX
    0.58
     <<<<<<<<<<<<<<
    0.56
    saco
    0.54
    relativeTime
    0.54
     playoff
    0.53
     playoffs
    0.52
    Activations Density 0.418%

    No Known Activations