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. 3-GEMMASCOPE-RES-16K
    6. 11214
    Prev
    Next
    INDEX
    Explanations

    terms related to medications and addiction, particularly focusing on methadone and heroin

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Carney
    -0.79
     Taub
    -0.78
     Jacinto
    -0.72
     numberWith
    -0.71
    </em>
    -0.70
    Hare
    -0.70
     MenuView
    -0.69
     Bhatt
    -0.69
     Ostro
    -0.69
    mali
    -0.68
    POSITIVE LOGITS
     juſ
    0.91
     Johnnie
    0.90
     berries
    0.89
     inſ
    0.83
     Diſ
    0.81
     Jefus
    0.81
    roland
    0.80
     Dieter
    0.79
     Shand
    0.79
     Thurston
    0.79
    Activations Density 1.361%

    No Known Activations