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. 73697
    Prev
    Next
    INDEX
    Explanations

    action verbs related to the concept of taking or receiving

    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
    VersionUID
    -0.58
     InputDecoration
    -0.52
     initComponents
    -0.52
    ValueStyle
    -0.48
     isInitialized
    -0.48
    PerformLayout
    -0.47
    udayaan
    -0.46
     ProgressDialog
    -0.45
    Personensuche
    -0.44
     endometriosis
    -0.44
    POSITIVE LOGITS
     taken
    1.24
     take
    1.24
    Take
    1.21
     Take
    1.19
    take
    1.16
     TAKE
    1.16
    taken
    1.15
    Taken
    1.14
     Taken
    1.12
     TAKEN
    1.07
    Activations Density 0.083%

    No Known Activations