© 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. 31-GEMMASCOPE-RES-16K
    11. 3365
    Prev
    Next
    INDEX
    Explanations

    expressions of anger and emotional turmoil

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    the word "anger" and related expressions of rage or intense displeasure.

    oai_token-act-pair · claude-4-5-haikuTriggered by @emiglarou
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_31/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ModelSerializer
    -0.56
    Życiorys
    -0.51
    jspx
    -0.50
    phosa
    -0.47
     bezeichneter
    -0.46
    StoryboardSegue
    -0.45
     '\\;'
    -0.42
    quelize
    -0.42
     TextAppearance
    -0.41
    ﹃
    -0.41
    POSITIVE LOGITS
     anger
    2.14
     angry
    2.05
     rage
    1.88
    angry
    1.71
    Angry
    1.70
     Anger
    1.70
    Anger
    1.70
     colère
    1.68
     Angry
    1.67
     angrily
    1.63
    Activations Density 0.510%

    No Known Activations