© 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-2-9B
    7. Residual Stream - 16k
    9. 31-GEMMASCOPE-RES-16K
    11. 3399
    Prev
    Next
    INDEX
    Explanations

    references to weddings and related events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    words and phrases related to weddings and bridal events.

    oai_token-act-pair · claude-4-5-haikuTriggered by @emiglarou
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_31/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Zapraszamy
    -0.34
    vallen
    -0.33
    awtextra
    -0.33
    zaw
    -0.30
    aperto
    -0.29
     suburban
    -0.29
    divine
    -0.29
    竖
    -0.28
    üstü
    -0.28
    snapshot
    -0.28
    POSITIVE LOGITS
     bridesmaids
    1.18
     grooms
    1.13
     bridesmaid
    1.13
     Brides
    1.11
     bride
    1.11
     bridal
    1.11
     groom
    1.10
     bridegroom
    1.02
     Bride
    1.01
     Groom
    1.00
    Activations Density 0.080%

    No Known Activations