© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 1-GEMMASCOPE-RES-16K
    11. 9721
    Prev
    Next
    INDEX
    Explanations

    instances of subjective evaluations of taste and preference

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 1-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_1/width_16k/average_l0_69
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.1.hook_resid_post
    Hook Layer
    1
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     stepped
    -0.42
     disambiguazione
    -0.42
     breached
    -0.41
    mess
    -0.41
     step
    -0.41
    farwydd
    -0.41
    Хьажоргаш
    -0.41
    iffany
    -0.40
    mig
    -0.40
    ospatial
    -0.39
    POSITIVE LOGITS
     perspective
    1.06
     taste
    1.01
     tastes
    0.98
     Taste
    0.95
     Perspective
    0.94
    Perspective
    0.89
    Taste
    0.89
    taste
    0.88
     Geschmack
    0.87
    perspective
    0.85
    Activations Density 0.293%

    No Known Activations