© 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-2-9B
    7. Residual Stream - 16k
    9. 34-GEMMASCOPE-RES-16K
    11. 12034
    Prev
    Next
    INDEX
    Explanations

    specific points in time or reference to time-related expressions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 34-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_34/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.34.hook_resid_post
    Hook Layer
    34
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     at
    -0.68
     ainfi
    -0.59
     للمعارف
    -0.55
     feroit
    -0.51
     toiminta
    -0.50
    Égypte
    -0.50
    sofá
    -0.49
     Tatsache
    -0.48
    isamment
    -0.48
    hilangan
    -0.47
    POSITIVE LOGITS
     juncture
    0.76
     expense
    0.71
     level
    0.70
     point
    0.64
     glance
    0.64
     intervals
    0.61
     locations
    0.55
    expense
    0.54
     stage
    0.53
     discretion
    0.51
    Activations Density 0.570%

    No Known Activations