© 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 EvalsExportsinterp-engineNEWAPI 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. 101260
    Prev
    Next
    INDEX
    Explanations

    technical terms and identifiers related to user agents and computing systems

    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
     ModelExpression
    -0.80
     <<<<<<<<<<<<<<
    -0.65
    InSection
    -0.63
     CreateTagHelper
    -0.63
    ValueStyle
    -0.62
    principalColumn
    -0.58
    tagHelperRunner
    -0.54
    expandindo
    -0.53
     GenerationType
    -0.53
     ExecuteAsync
    -0.52
    POSITIVE LOGITS
    userAgent
    1.27
    UserAgent
    0.89
     UA
    0.49
    Mozilla
    0.45
    userProfile
    0.44
     AssemblyCulture
    0.42
    WSER
    0.41
     followed
    0.41
    UA
    0.41
     getUser
    0.40
    Activations Density 0.003%

    No Known Activations