© 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-2-2B
    7. Residual Stream - 16k
    9. 10-GEMMASCOPE-RES-16K
    11. 5050
    Prev
    Next
    INDEX
    Explanations

    texts related to legal proceedings and criminal records

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    etor
    -0.55
    APOLIS
    -0.49
    いち
    -0.46
     Finder
    -0.44
    kla
    -0.43
    พล
    -0.43
     Preference
    -0.43
     presume
    -0.42
    Max
    -0.42
    emo
    -0.41
    POSITIVE LOGITS
    ViewFeatures
    0.58
     >=",
    0.57
    eterangan
    0.57
    IBOutlet
    0.56
     AspNetCore
    0.56
    IsContent
    0.56
     nahilalakip
    0.56
     prior
    0.56
     typelib
    0.55
     betweenstory
    0.55
    Activations Density 0.632%

    No Known Activations