© 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
    7. Residual Stream - 16k
    9. 3-GEMMASCOPE-RES-16K
    11. 8688
    Prev
    Next
    INDEX
    Explanations

    the word "save" and its variations, indicating a focus on conservation or preservation concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_3/width_16k/average_l0_90
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    -------------</
    -0.56
    dataclass
    -0.54
    
    -0.45
    ViewFeatures
    -0.44
    IsPostBack
    -0.44
    sonaro
    -0.42
    tgz
    -0.42
    UrlEncoded
    -0.41
     féminine
    -0.41
    ︙
    -0.41
    POSITIVE LOGITS
     save
    1.95
     Save
    1.41
    save
    1.33
     saves
    1.27
     SAVE
    1.22
    Save
    1.15
     saved
    1.09
    SAVE
    1.00
     Saves
    0.91
    saves
    0.91
    Activations Density 0.095%

    No Known Activations