© 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. 20-GEMMASCOPE-RES-16K
    11. 11579
    Prev
    Next
    INDEX
    Explanations

    legal terms and concepts related to awards and intellectual property rights

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

    Awards, permissions, or authorizations

    np_acts-logits-general · gemini-2.0-flash

    awards and privileges granted

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    COUVER
    -0.49
    FunctionFlags
    -0.47
    miques
    -0.47
     Theodo
    -0.43
    kirch
    -0.43
    multirow
    -0.43
    webElementXpaths
    -0.43
    README
    -0.42
    tangentMode
    -0.42
    poto
    -0.42
    POSITIVE LOGITS
     awarded
    1.51
     awarding
    1.40
     granted
    1.34
     granting
    1.32
     otorg
    1.30
     bestowed
    1.29
     conferred
    1.27
     bestow
    1.24
     Awarded
    1.21
     vergeben
    1.19
    Activations Density 0.396%

    No Known Activations