© 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-2-9B
    4. Residual Stream - 16k
    5. 13-GEMMASCOPE-RES-16K
    6. 6536
    Prev
    Next
    INDEX
    Explanations

    positive adjectives that express quality and excellence

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 13-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_13/width_16k/average_l0_132
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.13.hook_resid_post
    Hook Layer
    13
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     diejenigen
    -0.62
     eivät
    -0.62
     problémy
    -0.59
     neler
    -0.59
     těch
    -0.58
     jotka
    -0.58
    Ligações
    -0.58
     Wohnungen
    -0.58
     şeyler
    -0.57
     málo
    -0.57
    POSITIVE LOGITS
     a
    0.67
    ,
    0.64
     joint
    0.56
     another
    0.49
     Slat
    0.48
    rope
    0.48
     A
    0.48
     Joint
    0.47
     entire
    0.47
     strategy
    0.47
    Activations Density 0.882%

    No Known Activations