© 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-IT
    4. Residual Stream - 16k
    5. 9-GEMMASCOPE-RES-16K
    6. 3967
    Prev
    Next
    INDEX
    Explanations

    frequent references to the word "the" and its context in various phrases

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

    Word following "the" or "an"

    np_acts-logits-general · gemini-2.0-flash

    the/an followed by people or roles

    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
    :✨
    -0.59
    URLException
    -0.58
    ConstraintMaker
    -0.57
    GEBURTSDATUM
    -0.52
     schoenen
    -0.52
     CWE
    -0.48
     betweenstory
    -0.48
    Kilder
    -0.47
     فريبيس
    -0.47
    Appearances
    -0.47
    POSITIVE LOGITS
     people
    0.54
    ผู้
    0.52
     fellow
    0.51
    ؤلاء
    0.48
     civi
    0.47
     students
    0.46
     người
    0.46
     Chriftian
    0.45
    AddField
    0.44
     everybody
    0.43
    Activations Density 0.564%

    No Known Activations