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. 15-GEMMASCOPE-RES-16K
    6. 1505
    Prev
    Next
    INDEX
    Explanations

    instances of the word "Another."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_15/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     rhiz
    -0.67
     Lyme
    -0.67
    IGraphics
    -0.66
     cubs
    -0.65
     docx
    -0.65
    kod
    -0.63
     către
    -0.63
     liens
    -0.63
     assoluto
    -0.63
     copii
    -0.62
    POSITIVE LOGITS
     another
    0.95
     }}"></
    0.94
     Another
    0.92
    another
    0.92
    Another
    0.92
     ANOTHER
    0.91
    !("{}",
    0.90
    enumi
    0.77
    ChildScrollView
    0.75
     dozen
    0.74
    Activations Density 0.064%

    No Known Activations