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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 10-GEMMASCOPE-RES-16K
    11. 7861
    Prev
    Next
    INDEX
    Explanations

    phrases related to mathematical concepts and their transformations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_10/width_16k/average_l0_113
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Administrativna
    -0.76
     propOrder
    -0.70
     ainfi
    -0.64
     defaultstate
    -0.63
     verſch
    -0.62
     ſei
    -0.62
     AssemblyCompany
    -0.62
    ItemBackground
    -0.59
    enterOuterAlt
    -0.59
    
    -0.59
    POSITIVE LOGITS
     abstract
    0.31
     things
    0.30
     data
    0.30
     sev
    0.29
     concreto
    0.28
     ingeniería
    0.28
     utiles
    0.28
     complex
    0.27
     complexity
    0.27
     errors
    0.27
    Activations Density 2.619%

    No Known Activations