Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 65k
    5. 12-GEMMASCOPE-RES-65K
    6. 43202
    Prev
    Next
    INDEX
    Explanations

    instances of the word "bind" and its variations, indicating a focus on binding concepts or actions in the context of programming

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 12-gemmascope-res-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_12/width_65k/average_l0_72
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    RegressionTest
    -1.10
     nonUne
    -0.84
    AsUp
    -0.82
    SourceChecksum
    -0.80
     okuyayım
    -0.80
     autorytatywna
    -0.78
     calendriers
    -0.77
     Италијани
    -0.76
     kasarigan
    -0.76
    /*++
    -0.75
    POSITIVE LOGITS
    bind
    1.40
     bind
    1.06
     Bind
    1.01
     BIND
    0.94
    Bind
    0.93
     binds
    0.90
    BIND
    0.88
     Binding
    0.78
     binders
    0.69
     binder
    0.69
    Activations Density 0.001%

    No Known Activations