© 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. 15-GEMMASCOPE-RES-16K
    11. 5437
    Prev
    Next
    INDEX
    Explanations

    expressions of surprise or unexpected events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_15/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ⓧ
    -0.69
    QtCore
    -0.58
    HtmlAttribute
    -0.57
    Toward
    -0.57
    mmate
    -0.55
     actualité
    -0.54
     NavController
    -0.53
    stateProvider
    -0.53
    VIAF
    -0.53
    WriteTagHelper
    -0.51
    POSITIVE LOGITS
     surprise
    1.01
     Surprise
    1.00
     surprised
    0.92
     shock
    0.92
    Surprise
    0.88
     surpris
    0.87
     Shock
    0.87
    surprise
    0.87
     Jefus
    0.87
     SHOCK
    0.86
    Activations Density 0.167%

    No Known Activations