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-2-9B-IT
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 14363
    Prev
    Next
    INDEX
    Explanations

    terms associated with radar technology and its applications

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

    radar systems

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    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
    WEBPACK
    -0.50
     Seton
    -0.45
    Piece
    -0.44
     Portion
    -0.43
     vlož
    -0.43
    Pieces
    -0.43
    länge
    -0.41
     Bix
    -0.41
    Portion
    -0.41
     Con
    -0.40
    POSITIVE LOGITS
     radar
    1.41
     Radar
    1.30
    radar
    1.16
    Radar
    1.15
    ProgressHUD
    0.70
    PerformLayout
    0.68
    elerik
    0.64
     vigilancia
    0.63
    CppMethod
    0.63
    EndInit
    0.62
    Activations Density 0.002%

    No Known Activations