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-2-2B
    4. Residual Stream - 16k
    5. 6-GEMMASCOPE-RES-16K
    6. 6118
    Prev
    Next
    INDEX
    Explanations

    adjectives and adverbs that express varying degrees of intensity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 6-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_6/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.6.hook_resid_post
    Hook Layer
    6
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     termica
    -0.78
     roja
    -0.74
     vermelhas
    -0.69
     debout
    -0.65
     vettor
    -0.65
     rojas
    -0.64
     toscana
    -0.64
     pleaſure
    -0.63
     quelcon
    -0.63
    Either
    -0.63
    POSITIVE LOGITS
    iecie
    0.90
     very
    0.88
    
    0.77
     highly
    0.76
     extremely
    0.73
    Искәрмәләр
    0.69
    Lähteet
    0.67
    Abitanti
    0.65
     المعيارى
    0.65
    rawDesc
    0.64
    Activations Density 0.449%

    No Known Activations