© 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. 11-GEMMASCOPE-RES-16K
    11. 13771
    Prev
    Next
    INDEX
    Explanations

    expressions of anger and frustration

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Hook Layer
    11
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     merveille
    -0.58
    HEAST
    -0.56
    Données
    -0.53
    uttavia
    -0.52
    isNullOrEmpty
    -0.52
    anstalt
    -0.52
     avenir
    -0.49
     föruts
    -0.49
    Seeder
    -0.49
     strö
    -0.48
    POSITIVE LOGITS
     angry
    1.38
     anger
    1.34
     Anger
    1.30
     Angry
    1.23
    angry
    1.22
    Anger
    1.22
    Angry
    1.19
     enoj
    1.13
     colère
    1.12
     enraged
    1.10
    Activations Density 0.217%

    No Known Activations