© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 33-GEMMASCOPE-RES-16K
    11. 6089
    Prev
    Next
    INDEX
    Explanations

    phrases related to experiences and durations of time

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 33-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_33/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.33.hook_resid_post
    Hook Layer
    33
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Month
    -0.78
     resourceCulture
    -0.75
     month
    -0.75
    parsedMessage
    -0.73
    Month
    -0.73
     MONTH
    -0.73
    MONTH
    -0.68
    month
    -0.67
     Wochen
    -0.63
    一个月
    -0.63
    POSITIVE LOGITS
     decade
    1.52
     ten
    1.38
     years
    1.07
    decade
    1.06
    十年
    1.04
     Decade
    1.02
     zehn
    1.02
     seven
    1.02
     five
    0.99
    ten
    0.97
    Activations Density 0.485%

    No Known Activations