© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 104402
    Prev
    Next
    INDEX
    Explanations

    references to drug education and harm reduction initiatives

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

    Names of organizations, publications, and social/political movements, often appearing in formal text about foundations, political activities, or academic contexts. These include references to specific publications (like "Lotta Comunista"), organizations (like "Drug-Free World"), political entities, and research centers.

    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
     surla
    -0.66
    tvguidetime
    -0.62
     للاسماء
    -0.59
    XtraBars
    -0.57
    XmlAccessorType
    -0.57
     ब्रेकडाउन
    -0.57
     تضيفلها
    -0.54
     CreateTagHelper
    -0.53
     AssemblyCulture
    -0.53
    Coordonnées
    -0.53
    POSITIVE LOGITS
     Pastel
    0.32
     Ass
    0.31
    startActivity
    0.30
     cop
    0.30
     dams
    0.30
    {#
    0.30
     tam
    0.29
    アンス
    0.29
     Falun
    0.29
     gynhyrchwyd
    0.29
    Activations Density 0.023%

    No Known Activations