© 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-2-9B
    7. Residual Stream - 16k
    9. 0-GEMMASCOPE-RES-16K
    11. 8351
    Prev
    Next
    INDEX
    Explanations

    references to luck and "door" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 0-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_0/width_16k/average_l0_129
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    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
     onts
    -0.45
    ELING
    -0.42
     Conservative
    -0.42
     plaatsen
    -0.42
     الس
    -0.42
     cụ
    -0.42
     grecque
    -0.41
    jetty
    -0.40
    mobileqq
    -0.39
     onderhoud
    -0.39
    POSITIVE LOGITS
    Door
    0.81
     Door
    0.76
     door
    0.71
     Doors
    0.69
     doors
    0.66
     DOOR
    0.66
    door
    0.64
    Doors
    0.63
     lucky
    0.62
     thesis
    0.60
    Activations Density 0.171%

    No Known Activations