© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 11-GEMMASCOPE-RES-16K
    11. 5118
    Prev
    Next
    INDEX
    Explanations

    phrases that indicate purpose or intent for actions

    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
     Theſe
    -0.65
     myſelf
    -0.63
     Efq
    -0.60
     fubject
    -0.60
     houſe
    -0.59
    jsonwebtoken
    -0.58
     Monfieur
    -0.58
     ſever
    -0.57
     zipper
    -0.57
    naut
    -0.57
    POSITIVE LOGITS
     help
    0.67
     make
    0.62
     give
    0.61
     ensure
    0.58
    laterra
    0.58
    ISupport
    0.57
    ulario
    0.57
     enable
    0.57
     permitan
    0.55
    webElementXpaths
    0.55
    Activations Density 0.399%

    No Known Activations