© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 7-GEMMASCOPE-RES-16K
    6. 10276
    Prev
    Next
    INDEX
    Explanations

    references to mathematical labeling and notation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 7-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_7/width_16k/average_l0_69
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Hook Layer
    7
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     BoxFit
    -0.84
    PathVariable
    -0.70
    InSection
    -0.68
    IntentFilter
    -0.65
    Viitteet
    -0.64
    rrggbb
    -0.63
    ElementException
    -0.60
    endpush
    -0.60
    ButterKnife
    -0.60
    prefixer
    -0.60
    POSITIVE LOGITS
    TagMode
    1.25
    HtmlAttribute
    0.93
    AppCompat
    0.87
    RegistryLite
    0.76
     propOrder
    0.73
    ContentAsync
    0.72
     للاسماء
    0.69
    InputTagHelper
    0.65
    bootstrapcdn
    0.63
     matplotlib
    0.60
    Activations Density 0.022%

    No Known Activations