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. 13-GEMMASCOPE-RES-16K
    6. 387
    Prev
    Next
    INDEX
    Explanations

    phrases and terms related to technology solutions and products

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_13/width_16k/average_l0_84
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.13.hook_resid_post
    Hook Layer
    13
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     FEMALE
    -0.48
     female
    -0.46
     sorteo
    -0.45
     ItemStack
    -0.43
     getArguments
    -0.43
     sexuelle
    -0.43
     ennemis
    -0.43
    lwjgl
    -0.43
     sympy
    -0.43
     souvenir
    -0.43
    POSITIVE LOGITS
     software
    0.90
     integrated
    0.87
     scalable
    0.87
     capabilities
    0.85
     solutions
    0.83
     integration
    0.82
     integrate
    0.82
     capability
    0.80
     scalability
    0.80
     integrations
    0.79
    Activations Density 0.326%

    No Known Activations