© 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. 2-GEMMASCOPE-RES-16K
    11. 2384
    Prev
    Next
    INDEX
    Explanations

    terms related to promotions and advertisements

    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
    ght
    -0.51
    ReusableCell
    -0.51
     kö
    -0.51
    cang
    -0.50
     contr
    -0.50
    retweeted
    -0.49
     diverse
    -0.48
    αυ
    -0.48
    HALT
    -0.48
     enver
    -0.48
    POSITIVE LOGITS
     promotional
    1.15
    promo
    1.15
    Promotional
    1.11
     promo
    1.10
    TagMode
    1.10
     promotions
    1.03
    Promo
    1.02
     promos
    0.99
     Promotional
    0.98
    promotion
    0.97
    Activations Density 0.162%

    No Known Activations