© 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
    7. Residual Stream - 131k
    9. 20-GEMMASCOPE-RES-131K
    11. 103832
    Prev
    Next
    INDEX
    Explanations

    elements related to data structure keys and items

    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
     betweenstory
    -0.56
    EventQueue
    -0.34
    대
    -0.34
    glicher
    -0.34
    HandlerContext
    -0.33
    localctx
    -0.33
     Organisations
    -0.32
     Parlament
    -0.32
     Pros
    -0.31
    OP
    -0.31
    POSITIVE LOGITS
    arraycopy
    0.68
    GIVEREF
    0.57
    WriteBarrier
    0.53
    ApiModelProperty
    0.51
    Jîn
    0.50
    WidgetItem
    0.48
    RotationOrder
    0.48
    ConstraintMaker
    0.48
    envoi
    0.47
     propOrder
    0.47
    Activations Density 0.035%

    No Known Activations