© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 40-GEMMASCOPE-RES-16K
    11. 5487
    Prev
    Next
    INDEX
    Explanations

    phrases related to gifting and food

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 40-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_40/width_16k/average_l0_125
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.40.hook_resid_post
    Hook Layer
    40
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     صوتيه
    -0.55
    Personendaten
    -0.51
     للمعارف
    -0.51
     goederen
    -0.50
    BeginContext
    -0.49
    parsedMessage
    -0.49
    TypedDataSet
    -0.48
     zoude
    -0.45
    tagHelperRunner
    -0.45
     vermogen
    -0.44
    POSITIVE LOGITS
     accompaniment
    0.94
     replacement
    0.84
     companion
    0.81
     filler
    0.80
     substitute
    0.79
     decoration
    0.79
     addition
    0.79
     distraction
    0.75
     backup
    0.72
     centerpiece
    0.72
    Activations Density 0.440%

    No Known Activations