© 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. 9712
    Prev
    Next
    INDEX
    Explanations

    headers indicating sections or subsections in a document

    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
    WindowConstants
    -0.83
    ers
    -0.81
     Arend
    -0.74
     Torre
    -0.73
    acterium
    -0.73
    netinet
    -0.70
    <h2>
    -0.69
     Rhonda
    -0.69
    ductory
    -0.69
     FormControl
    -0.68
    POSITIVE LOGITS
    <h3>
    1.10
    Viitteet
    0.98
     EIS
    0.96
     dieux
    0.82
    Jereo
    0.80
     Jefus
    0.80
     ###
    0.77
    ypsies
    0.77
    guenos
    0.75
    jis
    0.75
    Activations Density 0.055%

    No Known Activations