© 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 - 16k
    9. 5-GEMMASCOPE-RES-16K
    11. 6127
    Prev
    Next
    INDEX
    Explanations

    phrases that indicate types or categories

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Guilt
    -0.60
     genieten
    -0.60
     Ballet
    -0.59
     remercier
    -0.57
     barnen
    -0.56
     évêque
    -0.55
     lắp
    -0.55
     stazione
    -0.54
     fährt
    -0.54
    たまた
    -0.54
    POSITIVE LOGITS
     Мексичка
    0.94
     kinds
    0.77
    fillType
    0.74
     ProtoMessage
    0.74
     snippetHide
    0.73
     types
    0.72
     scenario
    0.72
    Kinds
    0.70
    "):
    0.70
     SUDOC
    0.69
    Activations Density 0.130%

    No Known Activations