© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 21-GEMMASCOPE-RES-16K
    6. 8732
    Prev
    Next
    INDEX
    Explanations

    references to pharmaceutical transactions and collaborations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     BoxDecoration
    -0.52
    Sport
    -0.46
    bukkit
    -0.46
     ramos
    -0.45
    byshev
    -0.43
    getDoctrine
    -0.42
     vam
    -0.42
    chool
    -0.42
    로그램
    -0.42
    putstr
    -0.41
    POSITIVE LOGITS
     drug
    1.01
     pharma
    0.95
     biolog
    0.93
     pharmaceutical
    0.92
     Drug
    0.88
    drug
    0.86
    Drug
    0.84
     Pharma
    0.83
     Pharmaceutical
    0.83
     Pfizer
    0.80
    Activations Density 1.078%

    No Known Activations