© 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. 106291
    Prev
    Next
    INDEX
    Explanations

    sentences and phrases that express uncertainty or require user interaction

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

    Common function words (like "is", "are", "on", "the", "that") or auxiliary verbs that connect parts of sentences, often appearing in formal or informational texts like documentation, articles, and reports.

    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
    contentLoaded
    -0.76
     ModelExpression
    -0.75
    SharedDtor
    -0.71
    Personendaten
    -0.68
     ویکی‌پدی
    -0.68
    AndEndTag
    -0.65
    MessageOf
    -0.63
    principalTable
    -0.61
    الحياه
    -0.60
    StoryboardSegue
    -0.60
    POSITIVE LOGITS
     pitch
    0.37
     front
    0.35
     Pitch
    0.34
    atsch
    0.33
     An
    0.33
     Holy
    0.32
     المث
    0.32
     Kuch
    0.31
     kor
    0.31
     Jon
    0.30
    Activations Density 0.082%

    No Known Activations