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. 19-GEMMASCOPE-RES-16K
    6. 2212
    Prev
    Next
    INDEX
    Explanations

    references to legal terminology and measurement concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 19-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_19/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.19.hook_resid_post
    Hook Layer
    19
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     يتيمه
    -0.77
    :✨
    -0.76
    IsPostBack
    -0.73
    PerformLayout
    -0.73
    gonic
    -0.72
    Jeografia
    -0.67
    PreferredItem
    -0.67
    WriteTagHelper
    -0.67
    orghini
    -0.67
     الحره
    -0.67
    POSITIVE LOGITS
     for
    2.50
    for
    1.52
     для
    1.41
     untuk
    1.37
     für
    1.32
     FOR
    1.19
     voor
    1.16
     pentru
    1.13
     برای
    1.11
     för
    1.09
    Activations Density 0.678%

    No Known Activations