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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 11-GEMMASCOPE-RES-16K
    6. 13881
    Prev
    Next
    INDEX
    Explanations

    references to pumps and pumping mechanisms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Hook Layer
    11
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Falun
    -0.72
    //
    -0.71
    unhofer
    -0.71
    HttpSession
    -0.69
    ByExample
    -0.68
     Vettel
    -0.68
    drs
    -0.68
    CORBA
    -0.67
     skil
    -0.66
    toHaveBeenCalled
    -0.66
    POSITIVE LOGITS
     MOON
    0.95
     moon
    0.93
     moonlight
    0.91
    Moon
    0.89
     Pump
    0.89
    lunar
    0.88
     Moon
    0.85
    MOON
    0.85
    moon
    0.84
     moons
    0.83
    Activations Density 0.440%

    No Known Activations