© 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. 10-GEMMASCOPE-RES-16K
    11. 12376
    Prev
    Next
    INDEX
    Explanations

    references to surprise, shock, and disbelief in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    rawDesc
    -0.78
    Portail
    -0.68
    مصادر
    -0.66
    ništvo
    -0.64
    DispatchToProps
    -0.61
     Parcelable
    -0.60
     дописавши
    -0.60
    tabControl
    -0.58
    raszamy
    -0.58
    liferay
    -0.58
    POSITIVE LOGITS
     shocked
    1.39
    shocked
    1.24
     amazed
    1.23
     astonished
    1.20
     surprised
    1.18
     amazement
    1.12
     shocking
    1.12
     astonishment
    1.12
    surprised
    1.11
     stunned
    1.10
    Activations Density 0.202%

    No Known Activations