© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 34-GEMMASCOPE-RES-16K
    11. 10629
    Prev
    Next
    INDEX
    Explanations

    references to emotional states and conditions

    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
    previous
    -0.69
    Previous
    -0.66
     Subsequent
    -0.66
     Previous
    -0.65
     previous
    -0.64
     subsequent
    -0.61
     PREVIOUS
    -0.58
     précédents
    -0.54
    PREVIOUS
    -0.54
     предыду
    -0.53
    POSITIVE LOGITS
     currently
    2.80
     presently
    2.45
    currently
    2.41
     Currently
    2.38
    Currently
    2.36
     actuellement
    2.34
     derzeit
    2.23
     actualmente
    2.22
     atualmente
    2.19
     obecnie
    2.13
    Activations Density 0.897%

    No Known Activations