© 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. 102901
    Prev
    Next
    INDEX
    Explanations

    aspirations related to career and creative ambitions

    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
     worsened
    -0.36
    ILIO
    -0.35
     quasi
    -0.35
     практически
    -0.35
     différences
    -0.34
     former
    -0.33
    Almost
    -0.33
     Almost
    -0.32
     nearly
    -0.31
     quase
    -0.31
    POSITIVE LOGITS
    ChildScrollView
    0.71
     صوتيه
    0.70
    sizeCache
    0.69
     CreateTagHelper
    0.68
    aarrggbb
    0.66
     ModelExpression
    0.65
    Cyfarwyddwr
    0.63
     myſelf
    0.63
    Tembelea
    0.62
    цезда
    0.60
    Activations Density 0.035%

    No Known Activations