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 - 16k
    5. 12-GEMMASCOPE-RES-16K
    6. 8123
    Prev
    Next
    INDEX
    Explanations

    references to different types and characteristics of pipes

    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-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    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
    principalColumn
    -0.98
     Coliseum
    -0.84
     Quis
    -0.84
     honore
    -0.84
    gtest
    -0.84
    PhysRev
    -0.83
     estimés
    -0.82
     desorption
    -0.82
    SceneManagement
    -0.81
    PhysRevD
    -0.79
    POSITIVE LOGITS
     pipes
    1.37
     pipe
    1.31
    pipe
    1.30
     Pipe
    1.29
     Pipes
    1.20
    Pipes
    1.19
    Pipe
    1.17
    PIPE
    1.16
    Piper
    1.15
     Piper
    1.14
    Activations Density 0.187%

    No Known Activations