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. 9179
    Prev
    Next
    INDEX
    Explanations

    terms related to missile defense systems

    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
    CodedInputStream
    -0.53
     disponibilités
    -0.47
     AssemblyCompany
    -0.43
    pergillus
    -0.42
     empathetic
    -0.42
     mergeFrom
    -0.42
     Indemnity
    -0.42
     Helden
    -0.41
    aminya
    -0.41
     zipper
    -0.41
    POSITIVE LOGITS
     missile
    1.17
     launch
    1.14
     missiles
    1.12
     Launch
    1.08
     launcher
    1.05
     launching
    1.03
     launches
    0.99
     launchers
    0.99
     Launching
    0.95
    Launch
    0.94
    Activations Density 0.168%

    No Known Activations