© 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. 16-GEMMASCOPE-RES-65K
    6. 27639
    Prev
    Next
    INDEX
    Explanations

    medical and biochemical terms related to adenosine and opioids.

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

    naltrex", "naloxone", "anal", "buccal", "phthal"

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_65k/average_l0_128
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ی
    -0.71
    </blockquote>
    -0.70
    <blockquote>
    -0.69
    IRT
    -0.69
     osob
    -0.67
    ly
    -0.66
    s
    -0.66
    ు
    -0.66
    IRO
    -0.64
    nosti
    -0.63
    POSITIVE LOGITS
    al
    1.07
    AL
    1.05
     Ral
    1.04
     Leal
    1.02
     RAL
    1.01
     Kral
    1.01
    EReference
    1.00
    Ral
    0.99
     Smal
    0.98
    endpush
    0.96
    Activations Density 0.106%

    No Known Activations