© 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. 11-GEMMASCOPE-RES-16K
    6. 2271
    Prev
    Next
    INDEX
    Explanations

    terms related to trades and exchanges in a sports context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Hook Layer
    11
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    +#+#
    -0.84
     مشين
    -0.82
     '\\;'
    -0.73
     SEDS
    -0.70
     Monfieur
    -0.70
    WebServlet
    -0.67
    SerializedSize
    -0.67
    HtmlAttribute
    -0.64
    WebControls
    -0.63
     Juillet
    -0.63
    POSITIVE LOGITS
     exchange
    0.72
     exchanged
    0.70
     swap
    0.69
     traded
    0.69
    swap
    0.65
     exchanging
    0.63
     swapped
    0.62
     exchanges
    0.62
    exchange
    0.61
     Exchange
    0.60
    Activations Density 0.114%

    No Known Activations