© 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. 285
    Prev
    Next
    INDEX
    Explanations

    scientific terms and references related to statistical mechanics and thermodynamics

    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
     sûre
    -0.37
    Confira
    -0.37
     marinho
    -0.36
     elétrico
    -0.35
    Bakgrunnsstoff
    -0.35
     Constitución
    -0.35
     cerâmica
    -0.34
    ưới
    -0.34
     *
    -0.34
     pescoço
    -0.34
    POSITIVE LOGITS
    féle
    0.63
    ův
    0.61
    esque
    0.56
    ian
    0.55
    rungsseite
    0.55
    InputBorder
    0.52
    IVEREF
    0.50
    UserScript
    0.50
    IAN
    0.47
    Xna
    0.46
    Activations Density 0.721%

    No Known Activations