© 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. 104055
    Prev
    Next
    INDEX
    Explanations

    events, statements, and public announcements concerning social or political issues

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

    The highlighted portions often mark temporal references, locations, or context-setting phrases that establish when, where, or how events took place. This includes dates, time periods, places, or descriptive phrases that frame the surrounding narrative.

    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
    RTDA
    -0.42
    IActionResult
    -0.38
     imageNamed
    -0.35
    flashdata
    -0.34
    ViewImports
    -0.34
    脚注の使い方
    -0.34
    UserScript
    -0.33
    حات
    -0.32
     stamp
    -0.32
    StackNavigator
    -0.31
    POSITIVE LOGITS
     holidays
    0.54
     navideñas
    0.53
     navideño
    0.52
     navideños
    0.51
     Khusus
    0.50
     navideña
    0.50
     Komunikasi
    0.50
    parsedMessage
    0.50
    RenderAtEndOf
    0.49
     ferie
    0.47
    Activations Density 0.053%

    No Known Activations