© 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. 6455
    Prev
    Next
    INDEX
    Explanations

    terms related to historical context and previous states of being or actions

    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
     mittlerweile
    -1.05
     inzwischen
    -1.01
     obecnie
    -0.95
     eventually
    -0.93
     finalmente
    -0.91
     désormais
    -0.90
    eventually
    -0.90
     inmiddels
    -0.90
     henceforth
    -0.86
     finally
    -0.86
    POSITIVE LOGITS
     thought
    0.69
     думал
    0.58
     казалось
    0.56
    thought
    0.54
    以為
    0.52
     dominated
    0.51
     THOUGHT
    0.50
     relied
    0.50
    と言えば
    0.49
    といえば
    0.49
    Activations Density 0.557%

    No Known Activations