© 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. 3-GEMMASCOPE-RES-16K
    6. 272
    Prev
    Next
    INDEX
    Explanations

    terms related to stopping or pausing, particularly in contexts involving traffic or health

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     وتسجيلات
    -0.67
    ("]");
    -0.58
    Missi
    -0.50
    butuhkan
    -0.49
     Exteriores
    -0.48
    nolia
    -0.47
    felizmente
    -0.46
    πον
    -0.46
     glucocortico
    -0.46
     елның
    -0.45
    POSITIVE LOGITS
     stop
    2.23
     stops
    2.19
     Stops
    2.06
     Stop
    2.04
     stopping
    2.00
     stopped
    1.96
    Stop
    1.94
     STOP
    1.94
     Stopping
    1.93
    stop
    1.91
    Activations Density 0.268%

    No Known Activations