© 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. 20-GEMMASCOPE-RES-16K
    11. 3535
    Prev
    Next
    INDEX
    Explanations

    expressions of frustration and annoyance

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

    emotional frustration and complaints, particularly about repetitive or annoying experiences.

    oai_token-act-pair · claude-3-5-haiku-20241022Triggered by @neilrathi
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_16k/average_l0_68
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Биография
    -0.37
     Freiw
    -0.34
     voto
    -0.31
     envisioned
    -0.30
     inneren
    -0.30
     Anpass
    -0.29
     Arbeiter
    -0.28
     erfahren
    -0.28
     Auft
    -0.28
     Betriebs
    -0.28
    POSITIVE LOGITS
     annoying
    0.66
    efois
    0.66
     jerks
    0.66
     idiots
    0.65
     infuriating
    0.64
     assholes
    0.63
     gyhoeddwyd
    0.60
     annoys
    0.59
     crap
    0.58
     idiotic
    0.57
    Activations Density 0.219%

    No Known Activations