© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B-IT
    7. Residual Stream - 131k
    9. 9-GEMMASCOPE-RES-131K
    11. 81520
    Prev
    Next
    INDEX
    Explanations

    terms related to orthogonality and frameworks within mathematical contexts

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

    orthogonal

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_131k/average_l0_121
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     AssemblyCompany
    -0.43
    <bos>
    -0.40
    endwhile
    -0.40
     enquanto
    -0.34
     Enquanto
    -0.31
     quien
    -0.31
     decimos
    -0.30
     sẻ
    -0.29
     Artículos
    -0.29
    żeli
    -0.29
    POSITIVE LOGITS
     vuông
    2.70
     defaultstate
    0.87
     square
    0.72
     SQUARE
    0.70
     perpendicular
    0.68
     rectangular
    0.67
     cân
    0.66
    ⊥
    0.66
    pendicular
    0.65
    quare
    0.65
    Activations Density 0.002%

    No Known Activations