© 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. 103418
    Prev
    Next
    INDEX
    Explanations

    structured data entries, particularly those related to items and their attributes

    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
    KURZBESCHREIBUNG
    -0.64
    ValueStyle
    -0.63
    expandindo
    -0.63
    parsedMessage
    -0.63
    RegressionTest
    -0.60
     typelib
    -0.59
     noDo
    -0.57
    دانشنامهٔ
    -0.57
    Rhestr
    -0.57
    createCanvas
    -0.53
    POSITIVE LOGITS
     Friedman
    0.41
    而来
    0.36
     complexities
    0.36
     differently
    0.35
    IBIL
    0.35
     less
    0.35
     intricacies
    0.34
    Const
    0.34
     Smy
    0.34
     Ph
    0.33
    Activations Density 0.033%

    No Known Activations