© 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-2-2B
    7. Residual Stream - 16k
    9. 10-GEMMASCOPE-RES-16K
    11. 12910
    Prev
    Next
    INDEX
    Explanations

    expressions of anger and intense emotions in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    •Steering evals

    No Comments

    Negative Logits
    isNullOrEmpty
    -0.63
     föruts
    -0.61
     merveille
    -0.60
    uttavia
    -0.59
     dalamnya
    -0.59
     NSCoder
    -0.58
    Seeder
    -0.58
    flops
    -0.57
     surla
    -0.55
     Italijanski
    -0.55
    POSITIVE LOGITS
     angry
    1.43
     anger
    1.40
     Anger
    1.40
     Angry
    1.31
    Angry
    1.28
    angry
    1.27
    Anger
    1.27
     enoj
    1.18
     colère
    1.17
     rage
    1.16
    Activations Density 0.215%

    No Known Activations