© 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. 35-GEMMASCOPE-RES-16K
    11. 9466
    Prev
    Next
    INDEX
    Explanations

    references to historical events or milestones related to institutions or businesses

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 35-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_35/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.35.hook_resid_post
    Hook Layer
    35
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     vorige
    -0.43
     geçmiş
    -0.40
     tidligere
    -0.40
     når
    -0.38
    Når
    -0.38
     gestern
    -0.35
    刚才
    -0.35
    上次
    -0.34
     früher
    -0.34
     tidigare
    -0.33
    POSITIVE LOGITS
     subsequently
    2.14
     subsequent
    1.95
     thereafter
    1.89
     Subsequently
    1.81
     later
    1.80
     soon
    1.71
     Subsequent
    1.66
     posteriormente
    1.60
    Later
    1.55
     später
    1.55
    Activations Density 1.291%

    No Known Activations