Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 57317
    Prev
    Next
    INDEX
    Explanations

    key concepts related to programming, economics, and community engagement

    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
    //-->
    -0.28
    je
    -0.28
     I
    -0.27
     bezeichneter
    -0.25
    entieth
    -0.24
     gradova
    -0.24
    ade
    -0.24
     crossorigin
    -0.24
    o
    -0.23
    complexContent
    -0.23
    POSITIVE LOGITS
     Geiſt
    0.64
    shadowRadius
    0.63
    RegressionTest
    0.60
     Waſſer
    0.59
    principalColumn
    0.57
     otomatig
    0.55
    ValueStyle
    0.55
     gouver
    0.55
     kapture
    0.54
    CloseOperation
    0.54
    Activations Density 0.102%

    No Known Activations