© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 65k
    5. 20-GEMMASCOPE-RES-65K
    6. 444
    Prev
    Next
    INDEX
    Explanations

    connections between lifestyle choices and health outcomes

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

    topics related to the health impacts of night shift work

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

    healthy diet and nutrition

    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-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_65k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    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
    ArgsConstructor
    -0.59
    "]}
    -0.56
     odkazy
    -0.55
    lwjgl
    -0.54
    "}>
    -0.53
    GOTREF
    -0.52
    oa̍t
    -0.51
    ])))
    -0.50
    %");
    -0.50
    tagHelperRunner
    -0.49
    POSITIVE LOGITS
     diet
    1.78
     eating
    1.57
    diet
    1.49
     nutrition
    1.45
     eat
    1.37
     food
    1.36
     dietary
    1.35
     diets
    1.34
     dieta
    1.32
    Diet
    1.30
    Activations Density 0.402%

    No Known Activations