© 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. 33-GEMMASCOPE-RES-16K
    6. 642
    Prev
    Next
    INDEX
    Explanations

    references to the concept of order and arrangement

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 33-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_33/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.33.hook_resid_post
    Hook Layer
    33
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     незавершена
    -0.53
    featureID
    -0.49
     المعيارى
    -0.45
    httphttps
    -0.40
    IntoConstraints
    -0.40
     оригіналу
    -0.39
     disambiguazione
    -0.39
    //</
    -0.39
    ISupport
    -0.38
    jiny
    -0.37
    POSITIVE LOGITS
     order
    2.61
     ORDER
    2.19
     Order
    2.19
    order
    2.13
     ordering
    2.09
     ordem
    2.08
     orden
    2.03
    Order
    2.02
     ordre
    1.98
     ordered
    1.97
    Activations Density 1.141%

    No Known Activations