© 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 - 65k
    9. 0-GEMMASCOPE-RES-65K
    11. 9894
    Prev
    Next
    INDEX
    Explanations

    themes related to happiness and joy

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 0-gemmascope-res-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_0/width_65k/average_l0_73
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    Data Type
    float32
    Hook Name
    blocks.0.hook_resid_post
    Hook Layer
    0
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    擎
    -0.49
    classnames
    -0.49
    lid
    -0.47
     _
    -0.47
    mspace
    -0.47
    ray
    -0.47
    рот
    -0.46
     Bay
    -0.46
     Erzb
    -0.46
    ruhe
    -0.46
    POSITIVE LOGITS
     happiness
    1.63
     Happiness
    1.49
     happy
    1.38
    happiness
    1.38
    Happiness
    1.34
     HAPPY
    1.27
     happiest
    1.24
     happier
    1.17
     heureux
    1.17
     feliz
    1.16
    Activations Density 0.066%

    No Known Activations