© 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. 102117
    Prev
    Next
    INDEX
    Explanations

    various forms of writing and related activities

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

    References to writing in educational or publishing contexts, including assignments, essays, papers, poems, or stories that students or authors need to produce.

    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
    migrationBuilder
    -0.36
     navigu
    -0.36
     Abbot
    -0.35
    GOTREF
    -0.35
    GIVEREF
    -0.33
     tæ
    -0.33
     capitalists
    -0.32
    AddTagHelper
    -0.32
     Ruff
    -0.31
     keberadaan
    -0.31
    POSITIVE LOGITS
     essay
    0.69
     essays
    0.65
    Essay
    0.63
    djangoproject
    0.62
     Essay
    0.59
    WireFormatLite
    0.59
    作文
    0.57
    Essays
    0.57
    essay
    0.57
     Essays
    0.56
    Activations Density 0.009%

    No Known Activations