© 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-2-9B
    7. Residual Stream - 16k
    9. 37-GEMMASCOPE-RES-16K
    11. 4270
    Prev
    Next
    INDEX
    Explanations

    programming constructs and data structures related to arrays and sorting algorithms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 37-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_37/width_16k/average_l0_124
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.37.hook_resid_post
    Hook Layer
    37
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     surla
    -0.62
     kasarigan
    -0.60
     AssemblyProduct
    -0.58
    irvana
    -0.54
    lüğ
    -0.53
    xase
    -0.52
     autorytatywna
    -0.50
    ThroughAttribute
    -0.49
    persky
    -0.49
    hoeddwyd
    -0.48
    POSITIVE LOGITS
     ans
    0.62
    ans
    0.51
     nums
    0.48
    Ans
    0.44
    nums
    0.44
     dfs
    0.44
     solve
    0.44
     answer
    0.43
     dp
    0.42
     visited
    0.41
    Activations Density 0.357%

    No Known Activations