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. 18-GEMMASCOPE-RES-16K
    6. 15726
    Prev
    Next
    INDEX
    Explanations

    instructions related to eating habits and dining etiquette

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

    "slow" or "slowing."

    np_acts-logits-general · gemini-2.0-flash

    slow down

    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
     $__
    -0.55
     iprot
    -0.51
     blinded
    -0.51
     Infórmanos
    -0.48
    hot
    -0.47
     Balkon
    -0.47
    Immediately
    -0.46
     Immediately
    -0.46
     immediately
    -0.45
    canestro
    -0.43
    POSITIVE LOGITS
     slow
    2.56
     Slow
    2.42
    slow
    2.36
    Slow
    2.36
     slower
    2.19
     SLOW
    2.17
     slowest
    2.15
    SLOW
    2.00
     slowed
    1.98
     slows
    1.97
    Activations Density 0.297%

    No Known Activations