© 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. 18-GEMMASCOPE-RES-16K
    11. 276
    Prev
    Next
    INDEX
    Explanations

    terms related to eCommerce platforms and customer support

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

    Follows company or product names

    np_acts-logits-general · gemini-2.0-flash

    offering services, products, or availability

    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
     שוליים
    -0.69
    andExpect
    -0.59
     estekak
    -0.57
    Atsauces
    -0.55
     élus
    -0.54
    "?>
    -0.54
    PerformLayout
    -0.52
     Wiktionnaire
    -0.51
    脚注の使い方
    -0.50
     AttributeSet
    -0.49
    POSITIVE LOGITS
     offer
    1.18
     offering
    1.17
     offers
    1.14
     available
    1.10
     offered
    1.08
     availability
    0.99
    offering
    0.98
    offers
    0.97
    offered
    0.96
     tilby
    0.96
    Activations Density 0.329%

    No Known Activations