© 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. 31-GEMMASCOPE-RES-16K
    11. 2201
    Prev
    Next
    INDEX
    Explanations

    sentences with emotional reflections or personal experiences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    expressions of frustration, disappointment, or regret about failed expectations or outcomes.

    oai_token-act-pair · claude-4-5-haikuTriggered by @emiglarou
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_31/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.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     currently
    -0.94
     recently
    -0.91
     lately
    -0.90
    recently
    -0.80
     presently
    -0.78
     Currently
    -0.75
     Recently
    -0.74
    currently
    -0.74
     derzeit
    -0.74
     recent
    -0.72
    POSITIVE LOGITS
     was
    0.96
     hindsight
    0.84
     afterwards
    0.84
     afterward
    0.84
     retrospect
    0.77
     Afterward
    0.77
    Afterwards
    0.77
     Afterwards
    0.77
     było
    0.73
    Was
    0.70
    Activations Density 0.699%

    No Known Activations