© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 22-GEMMASCOPE-RES-16K
    6. 14805
    Prev
    Next
    INDEX
    Explanations

    phrases or words related to tips and advice

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

    "tip" and variants

    np_acts-logits-general · gemini-2.0-flash

    tip of or tiptronic

    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
     незавершена
    -0.63
     Lightboxes
    -0.62
    rália
    -0.59
     StatefulWidget
    -0.57
    tute
    -0.57
     Sabina
    -0.56
     Merdeka
    -0.56
    ąż
    -0.55
    bloc
    -0.54
     Initialized
    -0.54
    POSITIVE LOGITS
     Tip
    1.29
     tip
    1.27
    Tip
    1.26
     tips
    1.17
     Tips
    1.14
    TIP
    1.13
     TIP
    1.12
    Tips
    1.10
    tip
    1.09
    TIPS
    0.95
    Activations Density 0.077%

    No Known Activations