© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 27-GEMMASCOPE-RES-16K
    11. 10022
    Prev
    Next
    INDEX
    Explanations

    expressions of annoyance and frustration in social interactions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 27-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_27/width_16k/average_l0_118
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.27.hook_resid_post
    Hook Layer
    27
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    unlikely
    -0.34
    RTLI
    -0.31
    ImageIO
    -0.29
    ungkinan
    -0.28
     espagne
    -0.28
     onAnimation
    -0.27
    ropriate
    -0.26
     risco
    -0.26
     ligiloj
    -0.26
     allegiance
    -0.26
    POSITIVE LOGITS
     annoying
    1.78
     irritating
    1.63
     annoyance
    1.56
     annoy
    1.54
     annoys
    1.49
     irritate
    1.35
     frustrating
    1.34
     infuriating
    1.34
     irrit
    1.30
     irritation
    1.29
    Activations Density 0.409%

    No Known Activations