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. 6279
    Prev
    Next
    INDEX
    Explanations

    specific scientific terms and technical language related to materials and methods in research

    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
     estimés
    -0.64
     snippetHide
    -0.57
    
    -0.51
    webElementXpaths
    -0.51
     composed
    -0.49
    깥
    -0.49
     efficacement
    -0.47
     GENERATED
    -0.47
     LUMP
    -0.47
    enfance
    -0.46
    POSITIVE LOGITS
    aarrggbb
    0.73
    prefixer
    0.54
    indd
    0.53
    asonic
    0.51
    dafri
    0.50
    ->___
    0.48
     Based
    0.47
    وفاته
    0.47
    momix
    0.47
    +#+#
    0.46
    Activations Density 1.123%

    No Known Activations