© 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. 4470
    Prev
    Next
    INDEX
    Explanations

    references to authority or power structures

    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
    #+#
    -0.66
    めでとう
    -0.65
     whoſe
    -0.65
    )");
    -0.64
     becauſe
    -0.62
     ſeveral
    -0.61
     ſhe
    -0.61
    ("]");
    -0.61
     ſp
    -0.60
     itſelf
    -0.60
    POSITIVE LOGITS
     purposes
    1.54
     sake
    1.28
    purposes
    1.16
     Purposes
    1.04
     purpose
    0.91
     reasons
    0.89
    Purpose
    0.78
    reasons
    0.75
     Zwecke
    0.75
     Sake
    0.75
    Activations Density 0.940%

    No Known Activations