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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 14-GEMMASCOPE-RES-16K
    6. 7660
    Prev
    Next
    INDEX
    Explanations

    HTML tags and CSS class definitions related to user interface elements

    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
     nakalista
    -0.91
    addContainerGap
    -0.89
    parsedMessage
    -0.85
     Италијани
    -0.85
     BoxFit
    -0.81
     lenker
    -0.77
    хьтан
    -0.75
    Хьажоргаш
    -0.74
     Roskov
    -0.74
     المعيارى
    -0.73
    POSITIVE LOGITS
     between
    0.65
     space
    0.64
    spacer
    0.60
     spacing
    0.58
     spacer
    0.55
     break
    0.54
    space
    0.54
    Space
    0.53
     separation
    0.53
     gap
    0.52
    Activations Density 0.476%

    No Known Activations