© 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. 41-GEMMASCOPE-RES-16K
    11. 6642
    Prev
    Next
    INDEX
    Explanations

    references to future predictions and trends

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 41-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_41/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.41.hook_resid_post
    Hook Layer
    41
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    новниш
    -0.54
     later
    -0.46
    ppuden
    -0.45
     senere
    -0.45
    tagHelperRunner
    -0.42
     recent
    -0.41
     recentemente
    -0.41
    recent
    -0.40
     später
    -0.40
    Географиясе
    -0.40
    POSITIVE LOGITS
     generations
    0.96
     tense
    0.85
     prospects
    0.83
    proofing
    0.78
     Tense
    0.71
     proofing
    0.70
     plans
    0.65
     possibilities
    0.65
     directions
    0.63
     endeavors
    0.63
    Activations Density 0.211%

    No Known Activations