© 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. 35-GEMMASCOPE-RES-16K
    6. 6391
    Prev
    Next
    INDEX
    Explanations

    code-related elements, specifically syntax and structure of programming functions and objects

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 35-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_35/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.35.hook_resid_post
    Hook Layer
    35
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Whilst
    -0.79
     Amongst
    -0.75
    Whilst
    -0.72
     skall
    -0.68
     perchè
    -0.67
     amongst
    -0.65
     whilst
    -0.64
     = 
    -0.64
    
    -0.63
     diatas
    -0.62
    POSITIVE LOGITS
    akaian
    0.48
    yorsunuz
    0.46
    évé
    0.46
    entraî
    0.46
    MessageOf
    0.45
    Vidite
    0.44
     zufolge
    0.44
    nościo
    0.43
     ferons
    0.43
    GRect
    0.42
    Activations Density 0.107%

    No Known Activations