© 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. 473
    Prev
    Next
    INDEX
    Explanations

    references to Facebook and its related functionalities

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

    "Facebook" or "FB"

    np_acts-logits-general · gemini-2.0-flash

    facebook page

    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
    Personendaten
    -0.79
    AndroidJUnit
    -0.62
    RenderAtEndOf
    -0.54
     Regency
    -0.49
     vla
    -0.49
    ClientSize
    -0.48
     Peck
    -0.48
     Wol
    -0.48
    unhofer
    -0.48
    aarrggbb
    -0.48
    POSITIVE LOGITS
     Facebook
    2.02
    Facebook
    1.83
     facebook
    1.78
    facebook
    1.70
     FB
    1.64
     FACEBOOK
    1.62
     Fb
    1.55
     fb
    1.52
    FACEBOOK
    1.50
    FB
    1.32
    Activations Density 0.103%

    No Known Activations