© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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-IT
    7. Residual Stream - 131k
    9. 9-GEMMASCOPE-RES-131K
    11. 84815
    Prev
    Next
    INDEX
    Explanations

    words related to value or sentiment towards cherished and treasured items

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

    things cherished or treasured

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_131k/average_l0_121
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     informée
    -0.62
    DockStyle
    -0.56
    ExtendWith
    -0.53
    RoutingModule
    -0.52
    olingo
    -0.51
    Clik
    -0.50
     saturn
    -0.50
    swire
    -0.49
     illegally
    -0.49
     amput
    -0.49
    POSITIVE LOGITS
     cherished
    1.59
     cherish
    1.56
     treasured
    1.15
    precious
    0.82
     precious
    0.79
    treasure
    0.79
     cher
    0.77
     beloved
    0.75
    珍惜
    0.75
     Cher
    0.73
    Activations Density 0.002%

    No Known Activations