© 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. 30-GEMMASCOPE-RES-16K
    11. 8861
    Prev
    Next
    INDEX
    Explanations

    text related to systematic reviews and evaluations in healthcare

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Follows "but", "to", "and"

    np_acts-logits-general · gemini-2.0-flash

    utilize

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 30-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_30/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.30.hook_resid_post
    Hook Layer
    30
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     stuff
    -1.16
     thingy
    -1.08
     crappy
    -1.07
     weird
    -1.02
     freakin
    -1.01
     lousy
    -0.98
     goodies
    -0.98
     freaking
    -0.96
     whopping
    -0.95
     nasty
    -0.94
    POSITIVE LOGITS
     utilizing
    0.70
    mektedir
    0.68
     utilized
    0.66
    maktadır
    0.64
     utilize
    0.64
     Additionally
    0.62
     additional
    0.59
     utilizes
    0.59
     posiada
    0.58
    较为
    0.57
    Activations Density 10.186%

    No Known Activations