© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 15628
    Prev
    Next
    INDEX
    Explanations

    phrases related to legal terminology and concepts

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

    followed by prepositions

    np_acts-logits-general · gemini-2.0-flash

    states being options or conditions

    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
     impactful
    -0.77
     incentiv
    -0.76
     prioritize
    -0.67
     transitioning
    -0.66
     playbook
    -0.63
     onboarding
    -0.63
     impacts
    -0.59
     impacted
    -0.59
     fueled
    -0.59
     transitioned
    -0.59
    POSITIVE LOGITS
    faßt
    0.87
     Надо
    0.70
    findpost
    0.69
    luß
    0.69
    BeginContext
    0.67
     daß
    0.67
     mußten
    0.65
     mußte
    0.65
     eenig
    0.64
     وتسجيلات
    0.64
    Activations Density 0.863%

    No Known Activations