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. 16-GEMMASCOPE-RES-16K
    6. 14826
    Prev
    Next
    INDEX
    Explanations

    notable individuals or alumni from specific schools or institutions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Notable alumni/graduates

    np_acts-logits-general · gemini-2.0-flash

    alumni and former members

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     AssemblyCompany
    -0.65
     AssemblyCulture
    -0.62
    webElementXpaths
    -0.57
    kháu
    -0.57
    eqn
    -0.56
    Erreferentziak
    -0.56
    ServletRequest
    -0.49
    tente
    -0.48
     DRAWINGS
    -0.48
    Bioaccumulative
    -0.47
    POSITIVE LOGITS
     alumni
    0.85
     graduates
    0.76
     alum
    0.74
     alumnus
    0.72
     hervorge
    0.70
     grads
    0.69
     notable
    0.69
    alumni
    0.68
     Alumni
    0.68
     exports
    0.67
    Activations Density 0.327%

    No Known Activations