© 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. 22-GEMMASCOPE-RES-16K
    11. 2426
    Prev
    Next
    INDEX
    Explanations

    terms related to contracts and contractual obligations

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

    "contract" and related terms

    np_acts-logits-general · gemini-2.0-flash

    contractual terms and rights

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    •Steering experiments: Gemma 2-2B / 10-GEMMASCOPE-RES-16K

    No Comments

    Negative Logits
    httphttps
    -0.65
     Quizzes
    -0.61
     chrétienne
    -0.61
    HostException
    -0.61
    Portail
    -0.59
    ifolium
    -0.56
     PTE
    -0.56
    ValueGeneration
    -0.56
     desorption
    -0.56
    ISTRATION
    -0.56
    POSITIVE LOGITS
    ually
    1.21
    ual
    1.05
     Contracts
    0.82
    Contracts
    0.78
    ural
    0.75
     contracts
    0.74
    UAL
    0.68
    ///</
    0.65
     agreements
    0.59
    AnchorStyles
    0.58
    Activations Density 0.087%

    No Known Activations