© 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. 18-GEMMASCOPE-RES-16K
    11. 14265
    Prev
    Next
    INDEX
    Explanations

    phrases related to online shopping and affiliate marketing

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

    "Amazon"

    np_acts-logits-general · gemini-2.0-flash

    Amazon

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ngdoc
    -0.54
     незавершена
    -0.49
     insuffisamment
    -0.49
    SequentialGroup
    -0.47
    出版年
    -0.45
     itinéraires
    -0.45
    ęs
    -0.45
    下载附件
    -0.43
     ostavi
    -0.43
     feuille
    -0.42
    POSITIVE LOGITS
     Amazon
    1.35
    Amazon
    1.25
     amazon
    1.25
     AMAZON
    1.15
    amazon
    1.14
    amzn
    0.93
    AMAZ
    0.90
    亚马逊
    0.83
     Amaz
    0.75
    affiliate
    0.74
    Activations Density 0.065%

    No Known Activations