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. 20-GEMMASCOPE-RES-16K
    6. 626
    Prev
    Next
    INDEX
    Explanations

    terms related to "macrophages" and their various forms or contexts in biological discussions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Normdatei
    -0.90
    IsContent
    -0.90
    Vidite
    -0.86
     متعلقه
    -0.79
    contentLoaded
    -0.77
     محفوظة
    -0.77
    GraphicsUnit
    -0.77
     écoulé
    -0.77
    rungsseite
    -0.76
    Clik
    -0.76
    POSITIVE LOGITS
     Mac
    0.73
     OS
    0.72
     OSX
    0.65
     mac
    0.64
     MAC
    0.61
     os
    0.58
     Os
    0.55
    Mac
    0.51
     MacMillan
    0.51
    MAC
    0.51
    Activations Density 0.082%

    No Known Activations