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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 23-GEMMASCOPE-RES-16K
    6. 6401
    Prev
    Next
    INDEX
    Explanations

    references to collections and the act of collecting within various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 23-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_23/width_16k/average_l0_75
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.hook_resid_post
    Hook Layer
    23
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    GraphicsUnit
    -0.81
     AssemblyCulture
    -0.77
     GoogleFonts
    -0.72
    ButterKnife
    -0.71
    complexContent
    -0.69
     façons
    -0.67
     CreateTagHelper
    -0.67
    bootstrapcdn
    -0.67
    Спасылкі
    -0.65
     ***!
    -0.65
    POSITIVE LOGITS
    ObjectModel
    0.57
     nouns
    0.54
    Collections
    0.53
     cáps
    0.52
     gathers
    0.50
    ::<
    0.50
     data
    0.47
     nations
    0.47
     disposto
    0.46
     сведения
    0.46
    Activations Density 0.127%

    No Known Activations