© 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. 34-GEMMASCOPE-RES-16K
    11. 8924
    Prev
    Next
    INDEX
    Explanations

    technical instructions and descriptions related to systems and processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 34-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_34/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.34.hook_resid_post
    Hook Layer
    34
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     unsuccessfully
    -0.61
     leider
    -0.56
     propOrder
    -0.50
    残念ながら
    -0.49
    才行
    -0.46
     unsuccessful
    -0.45
     vulgares
    -0.43
    未能
    -0.43
    Poor
    -0.43
    nadequate
    -0.43
    POSITIVE LOGITS
     avoids
    1.14
    不必
    1.09
     saves
    1.07
     eliminates
    1.07
     rispar
    1.05
     nemus
    1.04
    无需
    1.04
     avoiding
    0.99
    不需要
    0.98
    也不用
    0.97
    Activations Density 0.731%

    No Known Activations