Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 16066
    Prev
    Next
    INDEX
    Explanations

    concepts and terms related to medications for addiction treatment

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    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
     الدولى
    -0.57
    ViewFeatures
    -0.55
    httphttps
    -0.55
     Roskov
    -0.55
     AppCompatTheme
    -0.51
    romos
    -0.50
    
    -0.50
    stützung
    -0.49
    期刊论文
    -0.48
    sene
    -0.48
    POSITIVE LOGITS
     addiction
    1.52
     Addiction
    1.36
    Addiction
    1.34
     addict
    1.29
     addicts
    1.24
     addictions
    1.21
     addicted
    1.19
     sobriety
    1.14
     rehab
    1.13
     relapse
    1.13
    Activations Density 0.314%

    No Known Activations