© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B-IT
    7. Residual Stream - 131k
    9. 20-GEMMASCOPE-RES-131K
    11. 78171
    Prev
    Next
    INDEX
    Explanations

    terms related to kinematics and transformations in physics

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

    relativistic boosts and transformations

    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
    fromnode
    -0.65
     tartalomajánló
    -0.64
    DockStyle
    -0.60
    EndGlobalSection
    -0.59
    ValueGeneration
    -0.59
     initComponents
    -0.57
    yntaxException
    -0.56
    findpost
    -0.54
    fjspx
    -0.53
    EndProject
    -0.53
    POSITIVE LOGITS
     relativistic
    0.60
    ativistic
    0.57
     Lorentz
    0.45
     relativity
    0.41
     Relativity
    0.36
     manifest
    0.35
    synchronized
    0.34
     strass
    0.34
     synch
    0.33
     physicians
    0.32
    Activations Density 0.050%

    No Known Activations