© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 10-GEMMASCOPE-RES-16K
    6. 13980
    Prev
    Next
    INDEX
    Explanations

    mathematical conditions and relationships involving estimators and moments

    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
     right
    -0.51
     bring
    -0.49
     паралле
    -0.49
     bringing
    -0.48
     diak
    -0.47
     traz
    -0.47
    яд
    -0.47
     mirror
    -0.47
    vity
    -0.46
     sento
    -0.46
    POSITIVE LOGITS
    RefNanny
    0.88
    ftagPool
    0.79
     FetchType
    0.78
     kaynağından
    0.75
     bpy
    0.69
    ViewChild
    0.67
     typelib
    0.67
    ArgsConstructor
    0.65
     bezeichneter
    0.64
     الحره
    0.64
    Activations Density 1.276%

    No Known Activations