© 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-IT
    7. Residual Stream - 131k
    9. 20-GEMMASCOPE-RES-131K
    11. 116324
    Prev
    Next
    INDEX
    Explanations

    phrases related to audience engagement and community interaction

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

    promoting to audiences and fans

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    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
    
    -0.59
     ComVisible
    -0.45
    MLLoader
    -0.41
    AndEndTag
    -0.40
    ]();
    -0.40
    RenderAtEndOf
    -0.39
    CppCodeGen
    -0.39
    //</
    -0.38
    PMailer
    -0.38
    Aiheesta
    -0.38
    POSITIVE LOGITS
     voters
    0.62
     audiences
    0.58
     audience
    0.52
     subscribers
    0.52
     viewers
    0.50
    subscribers
    0.48
    updateUser
    0.46
     fans
    0.46
     supporters
    0.45
     readers
    0.44
    Activations Density 0.048%

    No Known Activations