© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 14-GEMMASCOPE-RES-16K
    11. 7489
    Prev
    Next
    INDEX
    Explanations

    various forms of structure and organization in textual content

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 14-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_14/width_16k/average_l0_84
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.14.hook_resid_post
    Hook Layer
    14
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    нент
    -0.61
    UrlResolution
    -0.51
    MultipartFile
    -0.51
     subcategory
    -0.51
     طرف
    -0.50
     Stand
    -0.48
    attrs
    -0.48
     attrs
    -0.48
    ่
    -0.48
    GeneratedCode
    -0.48
    POSITIVE LOGITS
     layout
    1.01
     structure
    0.96
     arrange
    0.84
     structuring
    0.83
     Layout
    0.83
    布局
    0.82
     estruct
    0.81
     arrangement
    0.79
     estructura
    0.79
    structure
    0.78
    Activations Density 0.712%

    No Known Activations