© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 18-GEMMASCOPE-RES-16K
    6. 14161
    Prev
    Next
    INDEX
    Explanations

    content related to social media interactions and communications

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

    social media posts/activity

    np_acts-logits-general · gemini-2.0-flash

    social media posts and tweets

    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
    didSet
    -0.61
    GraphicsUnit
    -0.61
    Espèce
    -0.60
     دیکھیے
    -0.60
    лючение
    -0.60
    awsze
    -0.58
     bezoek
    -0.57
    FormBorderStyle
    -0.56
     orally
    -0.55
     hablamos
    -0.55
    POSITIVE LOGITS
     posting
    0.95
     posted
    0.92
     posts
    0.89
     screenshots
    0.87
     screenshot
    0.84
     captioned
    0.84
     postings
    0.78
     tweeted
    0.77
     caption
    0.75
     "@
    0.74
    Activations Density 0.086%

    No Known Activations