© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 4-GEMMASCOPE-RES-16K
    11. 13353
    Prev
    Next
    INDEX
    Explanations

    terms related to purchasing or buying actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.hook_resid_post
    Hook Layer
    4
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ValueStyle
    -0.76
     '\\;'
    -0.76
    Източници
    -0.59
    odeon
    -0.59
    tisgarh
    -0.57
    rillas
    -0.55
     Lovato
    -0.55
     שוליים
    -0.54
     récol
    -0.54
     Poehler
    -0.54
    POSITIVE LOGITS
     bought
    1.39
     buy
    1.34
     purchased
    1.32
     buying
    1.29
     buys
    1.28
     purchasing
    1.25
    bought
    1.24
     purchase
    1.21
    buy
    1.20
    purchased
    1.17
    Activations Density 0.333%

    No Known Activations