© 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. 1058
    Prev
    Next
    INDEX
    Explanations

    terms related to marijuana and hemp

    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
    orianCalendar
    -0.81
    มาะ
    -0.77
    gonic
    -0.74
    rekli
    -0.72
    atimes
    -0.71
     Cornel
    -0.69
    WithIdentifier
    -0.68
    oporosis
    -0.67
     Vise
    -0.66
    下载附件
    -0.66
    POSITIVE LOGITS
     CBD
    2.14
    CBD
    1.90
     Cbd
    1.75
     cbd
    1.66
    cbd
    1.63
     hemp
    1.12
     Hemp
    1.10
    Hemp
    1.00
    hemp
    0.95
     gummies
    0.94
    Activations Density 0.071%

    No Known Activations