Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 21-GEMMASCOPE-RES-16K
    6. 130
    Prev
    Next
    INDEX
    Explanations

    phrases and terms related to pricing and value in dining experiences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_21/width_16k/average_l0_129
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    lovakia
    -0.38
     medalla
    -0.38
     rooting
    -0.37
    庁
    -0.36
    ClCompile
    -0.36
     للمعارف
    -0.35
    öff
    -0.35
     Auff
    -0.34
     незавершена
    -0.34
    zuführen
    -0.34
    POSITIVE LOGITS
     prices
    1.09
     pricing
    0.99
     price
    0.98
    Prices
    0.93
    prices
    0.93
     Prices
    0.89
    price
    0.83
     getPrice
    0.83
    priced
    0.81
     priced
    0.81
    Activations Density 0.241%

    No Known Activations