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

    Neuronpedia

    APICircuit 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. 21-GEMMASCOPE-RES-16K
    6. 2774
    Prev
    Next
    INDEX
    Explanations

    emotional 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 @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    StoryboardSegue
    -0.57
     ExecuteAsync
    -0.54
     föruts
    -0.52
    assertNull
    -0.50
    mány
    -0.50
     Italijanski
    -0.50
     convite
    -0.49
    bida
    -0.47
    esModule
    -0.47
    Viitteet
    -0.46
    POSITIVE LOGITS
     anger
    2.08
     angry
    1.98
     rage
    1.73
    Anger
    1.73
     Anger
    1.71
    angry
    1.71
    Angry
    1.70
     Angry
    1.69
     angrily
    1.66
     enraged
    1.59
    Activations Density 0.400%

    No Known Activations