© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 2-GEMMASCOPE-RES-16K
    11. 4452
    Prev
    Next
    INDEX
    Explanations

    words associated with surprise or emotional reactions to shocking events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    SpringRunner
    -0.59
     calitate
    -0.51
     alberi
    -0.50
     rând
    -0.48
     http
    -0.48
    <i>
    -0.47
    OneToMany
    -0.46
    ibin
    -0.45
    erobe
    -0.45
    בת
    -0.45
    POSITIVE LOGITS
     shock
    3.87
     Shock
    3.50
    shock
    3.46
    Shock
    3.31
     SHOCK
    3.21
     shocks
    3.12
     shocked
    2.88
    shocked
    2.60
     shocking
    2.37
     surprise
    2.30
    Activations Density 0.059%

    No Known Activations