© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 12-GEMMASCOPE-RES-16K
    6. 6194
    Prev
    Next
    INDEX
    Explanations

    terms and concepts related to quantum gravity and spacetime

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 12-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_12/width_16k/average_l0_130
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     initComponents
    -0.64
     beginnetje
    -0.58
    expandindo
    -0.56
    Identyfik
    -0.55
    mittances
    -0.54
     Paglinawan
    -0.53
    ésultats
    -0.52
    withIdentifier
    -0.52
     OMITBAD
    -0.52
    +:+
    -0.51
    POSITIVE LOGITS
    PhysRevD
    0.49
    jsxFileName
    0.35
     spacetime
    0.35
    envoyer
    0.31
     fruta
    0.30
     pattes
    0.30
     године
    0.30
     convid
    0.29
    ジット
    0.29
     relativistic
    0.28
    Activations Density 1.169%

    No Known Activations