© 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-IT
    7. Residual Stream - 131k
    9. 9-GEMMASCOPE-RES-131K
    11. 96674
    Prev
    Next
    INDEX
    Explanations

    expressions of curiosity and personal interest

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

    asking for reasons or clarification

    np_acts-logits-general · gemini-2.5-flash-lite

    phrases that signal the writer/speaker referring to themselves or giving personal stance (first-person self-reference like "I", "I'm", "I know", "I mean", etc.).

    oai_token-act-pair · gpt-5-miniTriggered by @vetterc0
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_131k/average_l0_121
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    principalTable
    -0.56
    PMailer
    -0.49
    AntiForgeryToken
    -0.48
    WaitGroup
    -0.47
    ChildScrollView
    -0.47
     baud
    -0.46
     addSubview
    -0.46
    GOTREF
    -0.45
     Cad
    -0.45
     Judge
    -0.45
    POSITIVE LOGITS
    ordonnées
    0.37
     Roskov
    0.33
     çünkü
    0.31
    øse
    0.30
     belki
    0.30
     inquire
    0.30
     Савезне
    0.29
    rokken
    0.29
    basicConfig
    0.29
     lectores
    0.29
    Activations Density 0.271%

    No Known Activations