© 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 - 65k
    9. 20-GEMMASCOPE-RES-65K
    11. 1311
    Prev
    Next
    INDEX
    Explanations

    references to anniversaries and celebrations shared on social media

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

    mentions of social media and its features

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

    Instagram posts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_65k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Xna
    -0.72
    xhttp
    -0.67
    WebServlet
    -0.65
     salivary
    -0.60
    nemia
    -0.59
     Fax
    -0.59
     fevere
    -0.59
    Penulis
    -0.57
     Haywood
    -0.57
    بوابة
    -0.56
    POSITIVE LOGITS
     Instagram
    2.06
    Instagram
    1.86
     instagram
    1.73
    instagram
    1.60
     INSTAGRAM
    1.53
     Insta
    1.40
    Insta
    1.36
    INSTAGRAM
    1.34
     IG
    1.33
     insta
    1.27
    Activations Density 0.028%

    No Known Activations