Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 18-GEMMASCOPE-RES-16K
    6. 10318
    Prev
    Next
    INDEX
    Explanations

    references to collaborative programs and partnerships in innovation and research

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    after nouns of different topics

    np_acts-logits-general · gemini-2.0-flash

    specific situations and outcomes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     oczywiście
    -0.61
     infatti
    -0.58
    therefore
    -0.57
     quindi
    -0.56
    yntaxException
    -0.54
     ChromeDriver
    -0.52
    сунок
    -0.52
    なので
    -0.51
     ***!
    -0.50
     AssemblyProduct
    -0.49
    POSITIVE LOGITS
    <bos>
    1.24
     during
    0.84
    .",
    
    0.69
     amid
    0.69
    .
    
    0.67
    .[/
    0.67
     across
    0.66
     Paglinawan
    0.66
    .";
    
    0.65
    .\\
    0.64
    Activations Density 2.048%

    No Known Activations