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

    Neuronpedia

    APICircuit 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. 11-GEMMASCOPE-RES-16K
    6. 5829
    Prev
    Next
    INDEX
    Explanations

    references to the Bootstrap framework and its versions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Hook Layer
    11
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    expandindo
    -0.99
     تضيفلها
    -0.90
     zvuky
    -0.89
     الرياضيه
    -0.87
    帖最后由
    -0.86
    
    -0.85
     couverte
    -0.85
    ьаж
    -0.84
     Vario
    -0.83
     réfrig
    -0.82
    POSITIVE LOGITS
    bootstrap
    2.25
    Bootstrap
    1.58
     bootstrap
    1.58
     Bootstrap
    1.55
     bootstra
    1.05
     BOOT
    0.90
     Boot
    0.89
    Boot
    0.85
    boot
    0.83
    stdc
    0.81
    Activations Density 0.049%

    No Known Activations