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. 9474
    Prev
    Next
    INDEX
    Explanations

    references to military officials and their ranks

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

    Military ranks or titles

    np_acts-logits-general · gemini-2.0-flash

    military ranks and commands

    np_acts-logits-general · gemini-2.5-flash-lite
    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
    RegressionTest
    -0.57
    Autoritní
    -0.56
     createState
    -0.53
    rungsseite
    -0.52
     registration
    -0.51
    StructEnd
    -0.49
    diye
    -0.49
     Familienname
    -0.49
     vit
    -0.47
    registro
    -0.47
    POSITIVE LOGITS
     General
    0.86
    General
    0.85
     generals
    0.85
    general
    0.81
     Generals
    0.79
     general
    0.75
     GENERAL
    0.75
     Gen
    0.74
     Gener
    0.73
    Gen
    0.71
    Activations Density 0.178%

    No Known Activations