© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 2-GEMMASCOPE-RES-16K
    11. 9889
    Prev
    Next
    INDEX
    Explanations

    repeated occurrences of the token "di" in different contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_2/width_16k/average_l0_67
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    :✨
    -0.57
    المشاركات
    -0.56
     للمعارف
    -0.51
     Taktlose
    -0.49
    Билгалдахарш
    -0.49
     transférez
    -0.48
    новништво
    -0.48
     paral
    -0.47
    Viki
    -0.46
    ién
    -0.46
    POSITIVE LOGITS
     di
    0.61
    <th>
    0.61
    ip
    0.52
    djangoproject
    0.47
    findViewById
    0.46
     findViewById
    0.43
     GetEnumerator
    0.42
     ip
    0.42
    TableAdapter
    0.40
     milk
    0.40
    Activations Density 0.230%

    No Known Activations