© 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-2-2B
    4. Residual Stream - 16k
    5. 10-GEMMASCOPE-RES-16K
    6. 16086
    Prev
    Next
    INDEX
    Explanations

    instances of the word "great" and its variations, suggesting a focus on positivity and praise

    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
     متعلقه
    -0.85
     AssemblyTitle
    -0.83
     Lepidoptera
    -0.80
    Datuak
    -0.78
     Ludo
    -0.78
    losis
    -0.77
     narra
    -0.76
    epiece
    -0.75
    luna
    -0.75
     Lumia
    -0.74
    POSITIVE LOGITS
    GREAT
    1.41
     great
    1.36
     GREAT
    1.36
    great
    1.35
     Great
    1.34
    Great
    1.25
     big
    0.92
     greats
    0.91
     deal
    0.82
    DEAL
    0.82
    Activations Density 0.035%

    No Known Activations