© 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. 16-GEMMASCOPE-RES-16K
    6. 5684
    Prev
    Next
    INDEX
    Explanations

    descriptors related to the condition and features of items, particularly in a product review context

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

    Punctuation, especially periods

    np_acts-logits-general · gemini-2.0-flash

    selling prices and availability

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    
    -0.85
     betweenstory
    -0.72
    ISupport
    -0.72
     AssemblyVersion
    -0.69
    AndEndTag
    -0.66
    PerformLayout
    -0.64
    omock
    -0.63
    RenderAtEndOf
    -0.61
    ValueGeneration
    -0.61
     hObject
    -0.61
    POSITIVE LOGITS
     negotiable
    0.61
     Please
    0.59
     please
    0.58
     Rechnung
    0.55
     SOLD
    0.54
     Price
    0.54
     Ready
    0.54
     thiện
    0.53
     Negotiable
    0.52
    ONO
    0.51
    Activations Density 0.048%

    No Known Activations