© 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. 17-GEMMASCOPE-RES-16K
    11. 2013
    Prev
    Next
    INDEX
    Explanations

    processes and actions related to challenges in achieving something successfully

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 17-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_17/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.17.hook_resid_post
    Hook Layer
    17
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    webElementXpaths
    -0.97
    RenderAtEndOf
    -0.88
     defaultstate
    -0.86
    IsContent
    -0.79
    Hauptartikel
    -0.79
    StoryboardSegue
    -0.77
    parsedMessage
    -0.75
    igshid
    -0.74
    GenerationType
    -0.74
     <<<<<<<<<<<<<<
    -0.73
    POSITIVE LOGITS
     reliably
    0.77
     unless
    0.71
     efficacement
    0.69
     adequately
    0.69
     properly
    0.66
     anymore
    0.66
     truly
    0.64
     accurately
    0.64
     enää
    0.63
     realistically
    0.62
    Activations Density 0.646%

    No Known Activations