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. 5686
    Prev
    Next
    INDEX
    Explanations

    instances of the word "rest" and its variations in context

    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
    channelId
    -0.50
     způso
    -0.46
     Perusahaan
    -0.45
    neurial
    -0.45
     moeda
    -0.44
    cityId
    -0.44
      
    -0.44
     Oakley
    -0.43
     Byrne
    -0.43
    unternehmen
    -0.43
    POSITIVE LOGITS
     rest
    0.85
    rest
    0.84
    Rest
    0.78
     Rest
    0.76
     REST
    0.69
    REST
    0.68
     resten
    0.60
     BALANCE
    0.60
     reste
    0.59
     rested
    0.59
    Activations Density 0.172%

    No Known Activations