© 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. 5-GEMMASCOPE-RES-16K
    11. 13516
    Prev
    Next
    INDEX
    Explanations

    sentences that contain various forms of verbs and expressions related to actions and states of being

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    `,
    -0.86
    queryset
    -0.72
     
    -0.71
     ?>/
    -0.70
    \",\"
    -0.70
    :\/\/
    -0.69
    kloped
    -0.68
    /'+
    -0.68
    ？】
    -0.68
     getPage
    -0.68
    POSITIVE LOGITS
    .
    0.86
    。
    0.73
     habet
    0.70
     feldspar
    0.68
    しています
    0.67
     starfish
    0.67
    니다
    0.67
    lardır
    0.66
    あります
    0.65
    loroethane
    0.65
    Activations Density 0.044%

    No Known Activations