© 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. 18-GEMMASCOPE-RES-16K
    6. 4256
    Prev
    Next
    INDEX
    Explanations

    inquiries about the prices of items or costs associated with them

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

    Follows conjunctions or transitions

    np_acts-logits-general · gemini-2.0-flash

    got the

    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
    itarias
    -0.61
     abstrato
    -0.51
    orei
    -0.51
    kwij
    -0.49
    entur
    -0.48
    Euer
    -0.47
    Cooperation
    -0.47
    narod
    -0.46
     برگزار
    -0.46
    一个个
    -0.45
    POSITIVE LOGITS
     purchase
    0.98
     buying
    0.90
     purchased
    0.90
     purchasing
    0.86
     owning
    0.85
     Buying
    0.81
     Purchased
    0.78
     Purchase
    0.77
     upgrade
    0.77
     bought
    0.77
    Activations Density 0.189%

    No Known Activations