© 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 - 65k
    9. 13-GEMMASCOPE-RES-65K
    11. 17538
    Prev
    Next
    INDEX
    Explanations

    references to governmental or organizational entities, particularly those related to health and world events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 13-gemmascope-res-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_13/width_65k/average_l0_75
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    Data Type
    float32
    Hook Name
    blocks.13.hook_resid_post
    Hook Layer
    13
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     समीक्षाओं
    -1.11
     kaynağından
    -0.95
     itſelf
    -0.94
    GEBURTSDATUM
    -0.90
     оригіналу
    -0.90
    bootstrapcdn
    -0.88
     transfieras
    -0.88
    पया
    -0.87
     EClass
    -0.86
    adpleegd
    -0.85
    POSITIVE LOGITS
     anti
    0.59
     
    0.56
     $\
    0.56
     United
    0.56
     ri
    0.55
     inter
    0.54
     ""),
    0.52
    ku
    0.51
     central
    0.50
    "]))
    0.50
    Activations Density 0.153%

    No Known Activations