© 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. 25-GEMMASCOPE-RES-16K
    11. 8942
    Prev
    Next
    INDEX
    Explanations

    emotions and reactions related to surprise, disappointment, and being impressed

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.hook_resid_post
    Hook Layer
    25
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    •Emotion Validation

    No Comments

    Negative Logits
     للمعارف
    -0.65
    BeginInit
    -0.62
    cshtml
    -0.55
     ContentValues
    -0.55
    Smarty
    -0.53
    arounds
    -0.52
     préférences
    -0.52
     tilf
    -0.52
    PyExc
    -0.51
    setopt
    -0.51
    POSITIVE LOGITS
     about
    0.74
    不已
    0.64
    ьаж
    0.60
     betweenstory
    0.59
     darüber
    0.58
     disambiguazione
    0.58
     hearing
    0.57
    struck
    0.57
     bahwa
    0.56
     knowing
    0.55
    Activations Density 0.230%

    No Known Activations