© 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. 2966
    Prev
    Next
    INDEX
    Explanations

    statements and quotes related to political commentary and social issues

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

    associated with social media posts

    np_acts-logits-general · gemini-2.0-flash

    announcements via twitter

    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
     مشين
    -0.77
     विश्वसनीयता
    -0.69
    Хьажоргаш
    -0.66
    SharedCtor
    -0.65
    +#+#
    -0.64
    kloped
    -0.61
     चीज़ों
    -0.61
    +#+
    -0.58
     للاسماء
    -0.56
     переписи
    -0.53
    POSITIVE LOGITS
     tweeted
    2.27
     Twitter
    2.13
     tweeting
    2.12
     tweet
    2.05
     tweets
    1.98
     twitter
    1.88
    Twitter
    1.84
     Tweet
    1.69
     Tweets
    1.63
     Instagram
    1.62
    Activations Density 0.171%

    No Known Activations