© 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 - 16k
    9. 9-GEMMASCOPE-RES-16K
    11. 3957
    Prev
    Next
    INDEX
    Explanations

    usage of the French verb "faire" and its various forms in conversations about actions and inquiries

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

    Follows "What do" or "How can"

    np_acts-logits-general · gemini-2.0-flash

    what do you/they, how can i

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    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
     Numerade
    -0.59
     Interne
    -0.46
    檚
    -0.44
    jąca
    -0.43
     favoring
    -0.43
     BorderSide
    -0.43
    MV
    -0.42
     MV
    -0.42
    fjspx
    -0.42
    CBS
    -0.41
    POSITIVE LOGITS
     dovre
    0.60
     BoxFit
    0.56
     viņ
    0.52
     chúng
    0.50
    arangay
    0.50
     you
    0.49
     käyt
    0.47
     আম
    0.47
     lära
    0.46
     noDo
    0.46
    Activations Density 0.398%

    No Known Activations