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. 3-GEMMASCOPE-RES-16K
    6. 10889
    Prev
    Next
    INDEX
    Explanations

    URLs and references to social media platforms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     potash
    -0.58
     Abp
    -0.53
    følgelig
    -0.52
     igång
    -0.52
    уда
    -0.51
    phate
    -0.51
    ذك
    -0.50
    stehen
    -0.50
    djangoproject
    -0.50
     AppColors
    -0.50
    POSITIVE LOGITS
    UrlResolution
    0.61
    NameInMap
    0.58
    setViewName
    0.55
    GEBURTSDATUM
    0.54
    +#+
    0.52
    RouterModule
    0.52
    qrstuvwxyz
    0.52
    ettbewerb
    0.52
     folle
    0.52
    dataTables
    0.51
    Activations Density 0.141%

    No Known Activations