© 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-2-9B
    7. Residual Stream - 16k
    9. 33-GEMMASCOPE-RES-16K
    11. 10860
    Prev
    Next
    INDEX
    Explanations

    structured mathematical expressions and symbols in a formal context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 33-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_33/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.33.hook_resid_post
    Hook Layer
    33
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     center
    -0.37
     AKA
    -0.35
     greifen
    -0.35
    tagPool
    -0.34
    AKA
    -0.34
    Center
    -0.33
     Kompetenz
    -0.33
    ูน
    -0.32
     economica
    -0.30
     typelib
    -0.30
    POSITIVE LOGITS
    aligned
    0.73
     snippetHide
    0.68
     GenerationType
    0.67
     StringTokenizer
    0.64
    оргаш
    0.56
    ésultats
    0.56
     MenuView
    0.56
    utilisons
    0.54
    ruptedException
    0.54
    +#+#
    0.54
    Activations Density 0.188%

    No Known Activations