Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 22-GEMMASCOPE-RES-16K
    6. 5825
    Prev
    Next
    INDEX
    Explanations

    mentions of social media platforms and activities related to them

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

    Instagram

    np_acts-logits-general · gemini-2.0-flash

    Instagram

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Google
    -0.75
    Google
    -0.70
     yahoo
    -0.69
     Yahoo
    -0.69
     google
    -0.65
     tweeted
    -0.65
    Yahoo
    -0.65
     googled
    -0.64
     Skype
    -0.63
    DataBind
    -0.62
    POSITIVE LOGITS
     Reels
    1.10
     IG
    1.05
     Instagram
    1.03
     Stories
    0.98
     Inst
    0.92
     reels
    0.91
     Insta
    0.91
    Instagram
    0.90
     insta
    0.89
    Insta
    0.88
    Activations Density 0.056%

    No Known Activations