© 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. 15-GEMMASCOPE-RES-16K
    6. 13126
    Prev
    Next
    INDEX
    Explanations

    references to selling and transactions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_15/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ukone
    -0.63
     CreateTagHelper
    -0.61
     Parra
    -0.55
    }{*}{
    -0.55
     <=",
    -0.53
    INFINITY
    -0.53
    INFIN
    -0.53
     paramInt
    -0.52
    tedì
    -0.52
    matters
    -0.52
    POSITIVE LOGITS
     sell
    1.40
     selling
    1.32
    sell
    1.29
     sells
    1.28
     Verkauf
    1.28
    Sell
    1.26
     Sell
    1.23
     sale
    1.22
     sold
    1.17
     SELL
    1.17
    Activations Density 0.101%

    No Known Activations