© 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
    7. Residual Stream - 131k
    9. 20-GEMMASCOPE-RES-131K
    11. 102804
    Prev
    Next
    INDEX
    Explanations

    elements of programming or code structure

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_131k/average_l0_114
    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
    ihnachten
    -0.42
    曖昧さ回避
    -0.37
     defend
    -0.37
     anunciar
    -0.36
     regresar
    -0.36
    ніципа
    -0.35
    łbym
    -0.34
     mirando
    -0.34
    內容簡介
    -0.33
     inquire
    -0.33
    POSITIVE LOGITS
     Крем
    0.51
    principalTable
    0.47
    setVerticalGroup
    0.47
    Brick
    0.46
    GOTREF
    0.45
     وان
    0.44
    Experiment
    0.43
    hilangan
    0.43
    onts
    0.43
    Fie
    0.43
    Activations Density 0.025%

    No Known Activations