© 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. 31-GEMMASCOPE-RES-16K
    11. 10679
    Prev
    Next
    INDEX
    Explanations

    phrases and symbols related to programming or computational logic, particularly within the context of measurements and functions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    mathematical and numerical expressions with division operators and fractions.

    oai_token-act-pair · claude-4-5-haikuTriggered by @emiglarou
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_31/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.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     للاسماء
    -0.84
    hundred
    -0.65
     hundred
    -0.64
     hundreds
    -0.63
    contentLoaded
    -0.62
     Hundreds
    -0.61
    hundreds
    -0.60
     AspNetCore
    -0.60
    Hundreds
    -0.59
     <=",
    -0.58
    POSITIVE LOGITS
     three
    1.09
     four
    0.96
     five
    0.88
    three
    0.80
     six
    0.75
     two
    0.74
     três
    0.74
     trois
    0.72
     drei
    0.71
     THREE
    0.69
    Activations Density 1.207%

    No Known Activations