Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 1-GEMMASCOPE-RES-16K
    6. 9547
    Prev
    Next
    INDEX
    Explanations

    references to anger and related emotions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 1-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.1.hook_resid_post
    Hook Layer
    1
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    kadang
    -0.52
    modelBuilder
    -0.52
    BrowserModule
    -0.51
    '):
    
    -0.50
     Segovia
    -0.50
    ChildIndex
    -0.49
     XE
    -0.49
    Seeder
    -0.48
     délic
    -0.48
     SQLAlchemy
    -0.47
    POSITIVE LOGITS
     anger
    2.67
     angry
    2.41
     Anger
    2.20
     Angry
    2.12
    Angry
    2.10
    angry
    2.08
    Anger
    1.98
     angered
    1.65
     rage
    1.64
     furious
    1.60
    Activations Density 0.054%

    No Known Activations