© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 22-GEMMASCOPE-RES-16K
    6. 8621
    Prev
    Next
    INDEX
    Explanations

    content related to advertising, particularly in the context of digital marketing

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

    Advertising or analytics-related tokens

    np_acts-logits-general · gemini-2.0-flash

    ads, advertisers, targeting

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    OFFICIAL
    -0.54
    atzung
    -0.53
    hljs
    -0.52
    lave
    -0.51
    ########.
    -0.50
     Stiles
    -0.48
     fillet
    -0.44
    hlas
    -0.44
    Scénario
    -0.43
    RenderAtEndOf
    -0.43
    POSITIVE LOGITS
     ad
    0.92
     Ad
    0.89
     targeting
    0.85
     advertisers
    0.83
     ads
    0.81
     advertiser
    0.81
    Ad
    0.80
     Ads
    0.79
     bidding
    0.79
     CPM
    0.77
    Activations Density 0.159%

    No Known Activations