© 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. 20-GEMMASCOPE-RES-16K
    6. 14674
    Prev
    Next
    INDEX
    Explanations

    sports-related terminology and references to games

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_16k/average_l0_68
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ValueStyle
    -0.75
    ंदीखरीदारी
    -0.71
     queſta
    -0.64
     NSCoder
    -0.63
    ьаж
    -0.62
    IndentedString
    -0.61
     ſind
    -0.61
    InjectAttribute
    -0.60
    WebMethod
    -0.60
    الحياه
    -0.59
    POSITIVE LOGITS
     fit
    0.33
     finished
    0.31
     سینم
    0.30
     audience
    0.29
     orina
    0.28
     democratic
    0.28
     score
    0.27
     asistentes
    0.26
    олові
    0.26
    раздо
    0.26
    Activations Density 0.023%

    No Known Activations