© 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 - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 6858
    Prev
    Next
    INDEX
    Explanations

    terms related to deception and false information, particularly in a political context

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

    political conspiracy theories and inflammatory rhetoric about race, politics, and historical events.

    oai_token-act-pair · claude-3-5-haiku-20241022Triggered by @neilrathi
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_16k/average_l0_68
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    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
    bkz
    -0.52
    jspb
    -0.52
    Życiorys
    -0.50
     enfans
    -0.49
     ✭✭
    -0.49
    HtmlAttribute
    -0.49
    Morfologia
    -0.49
    upsi
    -0.49
    zeitung
    -0.48
    ValueStyle
    -0.47
    POSITIVE LOGITS
     ThemeData
    0.38
     dere
    0.35
     arşivlendi
    0.34
    StackNavigator
    0.34
     Italijanski
    0.31
    ngdoc
    0.31
    //
    0.31
    
    
    0.30
     Пло
    0.29
     Cataloging
    0.29
    Activations Density 0.306%

    No Known Activations