© 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. 1340
    Prev
    Next
    INDEX
    Explanations

    phrases and expressions related to 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 @ 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
    Not in Any Lists

    No Comments

    Negative Logits
    HtmlAttribute
    -0.57
    awtextra
    -0.55
     Ngb
    -0.53
    حوالہ
    -0.50
    Enlaces
    -0.49
     autorytatywna
    -0.49
    ędzy
    -0.49
    fering
    -0.49
    ="#"><
    -0.48
    soort
    -0.48
    POSITIVE LOGITS
     surprise
    2.63
     surprises
    2.33
     surprised
    2.29
    surprise
    2.20
     Surprise
    2.16
    Surprise
    2.09
     surprising
    2.02
     shock
    1.98
    surprised
    1.90
     surpris
    1.88
    Activations Density 0.475%

    No Known Activations