© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 13-GEMMASCOPE-RES-16K
    6. 7935
    Prev
    Next
    INDEX
    Explanations

    the repetition of the term "various" in different contexts

    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
     enfans
    -0.62
    ReusableCell
    -0.59
     pères
    -0.52
     âmes
    -0.52
    enschutzer
    -0.49
    Personendaten
    -0.48
     QtCore
    -0.48
    President
    -0.48
    
    -0.47
    yakarta
    -0.47
    POSITIVE LOGITS
     various
    1.40
    various
    1.30
    Various
    1.26
     Various
    1.24
     VARIOUS
    1.13
     diverses
    1.02
     diversos
    0.91
     numerous
    0.89
     diversas
    0.88
    各種
    0.86
    Activations Density 0.233%

    No Known Activations