© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 34-GEMMASCOPE-RES-16K
    11. 13602
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions and conditions related to polynomial degrees and physical fields

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 34-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_34/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.34.hook_resid_post
    Hook Layer
    34
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    seamnă
    -0.50
     werking
    -0.38
     diciendo
    -0.35
     étoient
    -0.35
     ayudado
    -0.34
     harán
    -0.34
     llegando
    -0.34
    StructEnd
    -0.34
     trouverez
    -0.34
     caminando
    -0.33
    POSITIVE LOGITS
     exhibit
    0.88
     Exhibit
    0.80
     exhibits
    0.78
    Exhibit
    0.72
     possess
    0.72
     exhib
    0.72
     Exhibits
    0.69
     exhi
    0.68
     behave
    0.65
     posses
    0.64
    Activations Density 2.441%

    No Known Activations