Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 113964
    Prev
    Next
    INDEX
    Explanations

    phrases related to networking and professional interactions

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

    LinkedIn introductions and networking

    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
    AntiForgeryToken
    -0.32
     empêcher
    -0.30
    ungkinan
    -0.30
     aimer
    -0.29
    WebServlet
    -0.27
     madera
    -0.27
     säker
    -0.25
    gdx
    -0.25
     adjunto
    -0.25
     inauguración
    -0.24
    POSITIVE LOGITS
     networking
    0.69
    httphttps
    0.68
     LinkedIn
    0.67
     Networking
    0.67
    twimg
    0.64
    Networking
    0.63
    évaluateur
    0.61
     Linkedin
    0.61
    ellido
    0.58
    LinkedIn
    0.58
    Activations Density 0.035%

    No Known Activations