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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsBlogSlackPrivacy & 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. 20-GEMMASCOPE-RES-16K
    6. 9999
    Prev
    Next
    INDEX
    Explanations

    expressions related to modal functionalities and user interface components

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Tikang
    -0.76
     CreateTagHelper
    -0.69
    itattu
    -0.64
    mybatisplus
    -0.62
    KommentareTeilen
    -0.59
    deviantart
    -0.58
    GenerationType
    -0.57
    chmal
    -0.57
    Бахар
    -0.55
     ProductService
    -0.54
    POSITIVE LOGITS
     dialog
    1.22
     Dialog
    1.09
     dialogue
    1.06
    Dialog
    1.04
    dialog
    1.04
     dialogues
    0.97
     popup
    0.97
     DIALOG
    0.92
     diálogo
    0.91
     pop
    0.90
    Activations Density 0.191%

    No Known Activations