© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 28-GEMMASCOPE-RES-16K
    11. 8121
    Prev
    Next
    INDEX
    Explanations

    references to social media platforms, specifically Instagram

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

    Social media mentions

    np_acts-logits-general · gemini-2.0-flash

    Instagram posts and activity

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 28-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_28/width_16k/average_l0_119
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.28.hook_resid_post
    Hook Layer
    28
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     utafitiHapana
    -0.54
     Majefty
    -0.39
     Plenum
    -0.39
     volunteers
    -0.39
     Linux
    -0.38
    /*
    -0.37
     DDoS
    -0.37
     PBS
    -0.37
     arşivlendi
    -0.37
    etCode
    -0.37
    POSITIVE LOGITS
     Instagram
    0.85
    Instagram
    0.79
     instagram
    0.75
     INSTAGRAM
    0.65
     Insta
    0.65
     insta
    0.65
    instagram
    0.63
    INSTAGRAM
    0.61
    Followers
    0.60
     Followers
    0.58
    Activations Density 0.064%

    No Known Activations