© 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. 22-GEMMASCOPE-RES-16K
    11. 5670
    Prev
    Next
    INDEX
    Explanations

    emotional expressions and reactions related to experiences

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

    Expressing feelings or opinions

    np_acts-logits-general · gemini-2.0-flash

    positive reactions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     feared
    -0.51
     resented
    -0.51
    estries
    -0.48
     dreaded
    -0.47
    famous
    -0.47
     عرو
    -0.47
    ριθ
    -0.47
     Studied
    -0.47
     Pliocene
    -0.46
     Known
    -0.46
    POSITIVE LOGITS
     impressed
    1.26
     intrigued
    1.08
     captivated
    1.03
     fascinated
    0.96
     attracted
    0.94
     enam
    0.92
     seduced
    0.91
     mesmer
    0.89
     moved
    0.89
     charmed
    0.88
    Activations Density 0.216%

    No Known Activations