© 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. 110277
    Prev
    Next
    INDEX
    Explanations

    mathematical concepts and terms related to structures and relationships in abstract settings

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

    i \in I, a \in A

    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
    OGND
    -0.65
    AccessorTable
    -0.63
     Biôgrafia
    -0.56
    contentLoaded
    -0.52
     للمعارف
    -0.52
    ſelf
    -0.49
    mountable
    -0.48
    SequentialGroup
    -0.47
    ſelves
    -0.46
    ngdoc
    -0.46
    POSITIVE LOGITS
    fluss
    0.42
     verfol
    0.38
     formulating
    0.38
     Juárez
    0.38
     vaga
    0.37
     clusters
    0.36
     bains
    0.36
     bibit
    0.36
     hrá
    0.36
     onOptions
    0.36
    Activations Density 0.311%

    No Known Activations