© 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. 5298
    Prev
    Next
    INDEX
    Explanations

    references to good and bad qualities or actions, specifically in the context of morality and principles

    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
     Versatile
    -0.35
     crossorigin
    -0.34
     actionMode
    -0.32
    terase
    -0.32
    intah
    -0.32
    確か
    -0.29
    納得
    -0.29
    ToMap
    -0.28
    ferential
    -0.28
    しゃれ
    -0.28
    POSITIVE LOGITS
     good
    3.33
    good
    3.08
    Good
    2.84
     GOOD
    2.78
     Good
    2.72
    GOOD
    2.67
     buenas
    2.27
     buena
    2.13
     gute
    2.03
     goede
    2.03
    Activations Density 0.591%

    No Known Activations