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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 27-GEMMASCOPE-RES-16K
    6. 9255
    Prev
    Next
    INDEX
    Explanations

    notable characteristics and specifications of classic cars

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 27-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_27/width_16k/average_l0_118
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.27.hook_resid_post
    Hook Layer
    27
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     product
    -0.38
    Product
    -0.34
     Widerstand
    -0.33
     Product
    -0.33
    Produkt
    -0.31
    ProductName
    -0.31
     diseñadores
    -0.31
     Produkt
    -0.31
    ProductCategory
    -0.31
    mamm
    -0.30
    POSITIVE LOGITS
    ConstraintMaker
    0.76
    MLLoader
    0.59
    complexContent
    0.59
    SourceChecksum
    0.58
    rungsseite
    0.58
     mileage
    0.57
     BoxFit
    0.56
     immaculate
    0.56
     Administrativna
    0.56
     للاسماء
    0.56
    Activations Density 0.056%

    No Known Activations