© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 106170
    Prev
    Next
    INDEX
    Explanations

    specific phrases and elements related to URLs and web applications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Whitespace tokens in formatted text, particularly in multiple-choice questions between option labels and content, or surrounding punctuation marks.

    eleuther_acts_top20 · claude-3-7-sonnet-20250219Triggered by @lu-christina
    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
     CURIAM
    -0.36
     Krank
    -0.36
     sh
    -0.35
    GeneratedMessage
    -0.34
    -0.33
    Etimología
    -0.32
     Super
    -0.32
    HomeAsUpEnabled
    -0.31
     super
    -0.31
     ne
    -0.31
    POSITIVE LOGITS
     linkovi
    0.74
    addCriterion
    0.56
    routeProvider
    0.52
    EDEFAULT
    0.51
    RTGC
    0.51
    URLException
    0.50
     Chwiliwch
    0.49
     choirs
    0.48
     ligiloj
    0.48
     protoimpl
    0.47
    Activations Density 0.168%

    No Known Activations