© 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. 9-GEMMASCOPE-RES-16K
    6. 9886
    Prev
    Next
    INDEX
    Explanations

    French articles and other definite and indefinite determiners

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_9/width_16k/average_l0_100
    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
    setVerticalGroup
    -0.98
     autorytatywna
    -0.90
    Tikang
    -0.81
    تقاوى
    -0.81
    hyrchwyd
    -0.80
    Personendaten
    -0.79
     мәкал
    -0.78
     فريبيس
    -0.78
    httphttps
    -0.77
    InstrumentedTest
    -0.77
    POSITIVE LOGITS
     the
    0.96
     la
    0.87
    The
    0.79
     την
    0.75
     The
    0.75
     THE
    0.68
     die
    0.67
    the
    0.66
     las
    0.65
     their
    0.63
    Activations Density 0.043%

    No Known Activations