© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 10-GEMMASCOPE-RES-16K
    6. 4067
    Prev
    Next
    INDEX
    Explanations

    repeated use of the word "whose."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     avanti
    -0.63
    i
    -0.62
     őket
    -0.60
     phú
    -0.60
     llorando
    -0.58
     tillegg
    -0.56
     Tatsache
    -0.55
     Pliny
    -0.53
    or
    -0.52
    e
    -0.52
    POSITIVE LOGITS
    Whose
    1.50
     Whose
    1.41
    whose
    1.31
     whose
    1.21
     whoſe
    1.20
     whofe
    1.18
    '))
    
    1.06
    ')}
    1.03
    }$}
    1.02
    wheres
    1.01
    Activations Density 0.038%

    No Known Activations