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. 17-GEMMASCOPE-RES-65K
    6. 28530
    Prev
    Next
    INDEX
    Explanations

    instances of the word "concat" in programming contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 17-gemmascope-res-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_17/width_65k/average_l0_125
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    Data Type
    float32
    Hook Name
    blocks.17.hook_resid_post
    Hook Layer
    17
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    VIAF
    -0.85
    awtextra
    -0.83
    InputTagHelper
    -0.74
    HasAnnotation
    -0.67
    Rüyada
    -0.67
     HasFactory
    -0.67
     EdgeInsets
    -0.67
    ‍
    -0.66
     onlyOwner
    -0.66
    }{*}{
    -0.65
    POSITIVE LOGITS
     concat
    1.12
    Concat
    1.05
    concat
    0.99
     concatenation
    0.72
     concaten
    0.70
    concaten
    0.68
    enaam
    0.68
     vad
    0.64
    caten
    0.63
     therewith
    0.61
    Activations Density 0.022%

    No Known Activations