© 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. 24-GEMMASCOPE-RES-16K
    11. 7935
    Prev
    Next
    INDEX
    Explanations

    references to personal possessions and specific item descriptions

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

    Following prepositions or punctuation

    np_acts-logits-general · gemini-2.0-flash

    purchased items from suppliers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_24/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    发表于
    -0.57
    Билгалдахарш
    -0.47
    transQ
    -0.47
    Искәрмәләр
    -0.45
    Personendaten
    -0.41
    //</
    -0.41
    rungsseite
    -0.40
    Trichloroethane
    -0.40
    twimg
    -0.39
     فريبيس
    -0.39
    POSITIVE LOGITS
     purchase
    0.61
     purchased
    0.60
     inexpensive
    0.59
     Ebay
    0.57
    purchase
    0.56
    purchased
    0.56
     ebay
    0.56
    手に入
    0.56
    ebay
    0.55
     cheap
    0.55
    Activations Density 0.314%

    No Known Activations