© 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. 0-GEMMASCOPE-RES-16K
    11. 5274
    Prev
    Next
    INDEX
    Explanations

    expressions of frustration and irritation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 0-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_0/width_16k/average_l0_105
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.hook_resid_post
    Hook Layer
    0
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    素晴らしい
    -0.64
    excellents
    -0.61
     amazing
    -0.60
    amazing
    -0.58
     marvellous
    -0.57
     merveille
    -0.55
     magnificent
    -0.54
     вікі
    -0.54
    unjang
    -0.54
     prachtige
    -0.53
    POSITIVE LOGITS
     frustrated
    1.21
     anxious
    1.17
     irritated
    1.16
     nervous
    1.11
     embarrassed
    1.09
     annoyed
    1.09
     impatient
    1.08
     reluctant
    1.07
     hesitant
    1.06
     apprehensive
    1.05
    Activations Density 2.990%

    No Known Activations