© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 21-GEMMASCOPE-RES-16K
    11. 794
    Prev
    Next
    INDEX
    Explanations

    references to transactions related to buying and selling, particularly in real estate contexts

    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
    COUVER
    -0.54
     InputDecoration
    -0.53
    cplusplus
    -0.48
    mobileqq
    -0.47
    이션
    -0.45
    msgTypes
    -0.45
     tardi
    -0.45
    ]));
    -0.45
     సౌకర్య
    -0.44
    kover
    -0.43
    POSITIVE LOGITS
     selling
    3.12
     sell
    3.09
     sold
    3.01
     sale
    2.98
     sells
    2.87
     Selling
    2.69
    Selling
    2.61
     Sell
    2.61
    sold
    2.60
    selling
    2.59
    Activations Density 0.392%

    No Known Activations