© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 14363
    Prev
    Next
    INDEX
    Explanations

    phrases related to scientific studies of biological interactions and processes

    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
    ็จ
    -0.35
    lwjgl
    -0.28
    bereits
    -0.28
     exécu
    -0.27
    roupa
    -0.26
    ANTAGES
    -0.26
     Verfü
    -0.26
     akzep
    -0.25
     duquel
    -0.25
    eseorang
    -0.25
    POSITIVE LOGITS
     study
    2.50
     analysis
    2.38
     studying
    2.16
     analyses
    2.13
    study
    2.08
     studies
    2.08
     analyze
    2.08
     analyse
    2.08
     studied
    2.06
     analyzing
    2.03
    Activations Density 2.824%

    No Known Activations