© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 65k
    9. 16-GEMMASCOPE-RES-65K
    11. 31339
    Prev
    Next
    INDEX
    Explanations

    instances of "we" indicating a collective subject or perspective

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_65k/average_l0_128
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ligiloj
    -0.62
    Šaltiniai
    -0.60
    BeginContext
    -0.60
    ########.
    -0.56
     vPvB
    -0.55
    ]--;
    -0.55
    kot
    -0.54
    SharedDtor
    -0.54
     ga
    -0.53
    @{
    -0.53
    POSITIVE LOGITS
    modelBuilder
    0.75
     verder
    0.56
     Kreuz
    0.55
    ↵
    0.52
     urm
    0.51
     Efq
    0.51
     ISTAT
    0.50
     sighting
    0.50
    section
    0.49
     Mercan
    0.49
    Activations Density 0.000%

    No Known Activations