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. 24-GEMMASCOPE-RES-16K
    6. 8303
    Prev
    Next
    INDEX
    Explanations

    references to web development technologies and tools

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

    Code repositories and related terms

    np_acts-logits-general · gemini-2.0-flash

    GitHub repositories and code

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    GraphicsUnit
    -0.65
     Archivado
    -0.52
    
    -0.50
    呵呵
    -0.49
    '],'
    -0.48
     Arkivert
    -0.47
     Arxivat
    -0.47
    >>>>>>>>
    -0.47
    ).]
    -0.47
    ";}
    -0.45
    POSITIVE LOGITS
     GitHub
    0.82
     repo
    0.80
     🚀
    0.77
     Github
    0.76
     🎉
    0.75
     👋
    0.73
     README
    0.72
     Jupyter
    0.70
     React
    0.69
     Docker
    0.68
    Activations Density 1.055%

    No Known Activations