© 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. 6107
    Prev
    Next
    INDEX
    Explanations

    legal and legislative references related to health and cancer screening

    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
     subsequently
    -0.65
     Subsequently
    -0.63
    较为
    -0.63
    mektedir
    -0.61
    であるが
    -0.60
     obecnie
    -0.57
     Additionally
    -0.57
    maktadır
    -0.56
     utilizing
    -0.56
     previously
    -0.55
    POSITIVE LOGITS
     stuff
    1.19
     thingy
    1.18
     goodies
    1.12
     yummy
    1.09
     weird
    1.04
     freakin
    1.03
     whopping
    1.03
     pretty
    1.02
     crappy
    1.02
     nasty
    1.01
    Activations Density 3.713%

    No Known Activations