© 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. 8387
    Prev
    Next
    INDEX
    Explanations

    phrases that emphasize the word "the" and its variations, often in conjunction with other contextual elements

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

    the definite article "the" at the beginning of prepositional phrases.

    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
     вовсе
    -0.35
     dalam
    -0.33
     Reinh
    -0.32
     within
    -0.32
     des
    -0.31
     extremo
    -0.30
     section
    -0.30
    sez
    -0.29
     precum
    -0.29
     kasarigan
    -0.28
    POSITIVE LOGITS
     regard
    1.20
     regards
    1.19
     behulp
    0.98
    regard
    0.97
    regards
    0.92
     hjälp
    0.90
     Regard
    0.84
     OFDb
    0.82
     respect
    0.80
     Regards
    0.78
    Activations Density 0.244%

    No Known Activations