© 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. 20-GEMMASCOPE-RES-131K
    11. 66451
    Prev
    Next
    INDEX
    Explanations

    terms related to geometric measurements and spatial relationships

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

    midpoints and projections

    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
     فريبيس
    -0.69
     queſta
    -0.62
     $_(
    -0.57
    tattoo
    -0.52
    ResponseWriter
    -0.52
    riwal
    -0.52
    Wirtschaft
    -0.51
    MemoryWarning
    -0.50
     transférez
    -0.49
     Monfieur
    -0.49
    POSITIVE LOGITS
     trung
    0.53
    penup
    0.44
     middle
    0.43
     midpoint
    0.41
     mid
    0.40
    กลาง
    0.40
     mitad
    0.39
     promedio
    0.37
     average
    0.37
     metade
    0.36
    Activations Density 0.005%

    No Known Activations